INC4AI commited on
Commit
ae3169c
·
verified ·
1 Parent(s): c764a88

Upload quantized model Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-AutoRound-W4A16-Tuning

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - quantized
7
+ - w4a16
8
+ - autoround
9
+ - low-bit-open-llm-leaderboard
10
+ ---
11
+
12
+ # Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-AutoRound-W4A16-Tuning
13
+
14
+ ## Model Details
15
+
16
+ This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of [nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451](https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451) generated by [AutoRound](https://github.com/intel/auto-round). Please follow the license of the original model.
17
+
18
+ ## Quantization Details
19
+
20
+ | Attribute | Value |
21
+ |-----------|-------|
22
+ | Base Model | [nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451](https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451) |
23
+ | Quantization Tool | [AutoRound](https://github.com/intel/auto-round) |
24
+ | Quantization Scheme | W4A16 |
25
+ | Quantized Size | 18009 MB |
26
+
27
+ ## Evaluation Results
28
+
29
+ | Task | Accuracy |
30
+ |------|----------|
31
+ | hellaswag | 0.6569 |
32
+ | mmlu | 0.8512 |
33
+ | mmlu_abstract_algebra | 0.7700 |
34
+ | mmlu_anatomy | 0.8444 |
35
+ | mmlu_astronomy | 0.9342 |
36
+ | mmlu_business_ethics | 0.8200 |
37
+ | mmlu_clinical_knowledge | 0.9057 |
38
+ | mmlu_college_biology | 0.9653 |
39
+ | mmlu_college_chemistry | 0.6800 |
40
+ | mmlu_college_computer_science | 0.8400 |
41
+ | mmlu_college_mathematics | 0.7100 |
42
+ | mmlu_college_medicine | 0.8844 |
43
+ | mmlu_college_physics | 0.7059 |
44
+ | mmlu_computer_security | 0.8700 |
45
+ | mmlu_conceptual_physics | 0.9447 |
46
+ | mmlu_econometrics | 0.8158 |
47
+ | mmlu_electrical_engineering | 0.8345 |
48
+ | mmlu_elementary_mathematics | 0.8598 |
49
+ | mmlu_formal_logic | 0.7460 |
50
+ | mmlu_global_facts | 0.5700 |
51
+ | mmlu_high_school_biology | 0.9581 |
52
+ | mmlu_high_school_chemistry | 0.8325 |
53
+ | mmlu_high_school_computer_science | 0.9200 |
54
+ | mmlu_high_school_european_history | 0.9030 |
55
+ | mmlu_high_school_geography | 0.9444 |
56
+ | mmlu_high_school_government_and_politics | 0.9896 |
57
+ | mmlu_high_school_macroeconomics | 0.9359 |
58
+ | mmlu_high_school_mathematics | 0.6407 |
59
+ | mmlu_high_school_microeconomics | 0.9538 |
60
+ | mmlu_high_school_physics | 0.8477 |
61
+ | mmlu_high_school_psychology | 0.9560 |
62
+ | mmlu_high_school_statistics | 0.9028 |
63
+ | mmlu_high_school_us_history | 0.9265 |
64
+ | mmlu_high_school_world_history | 0.9494 |
65
+ | mmlu_human_aging | 0.8475 |
66
+ | mmlu_human_sexuality | 0.9160 |
67
+ | mmlu_humanities | 0.7968 |
68
+ | mmlu_international_law | 0.9256 |
69
+ | mmlu_jurisprudence | 0.8889 |
70
+ | mmlu_logical_fallacies | 0.9202 |
71
+ | mmlu_machine_learning | 0.7321 |
72
+ | mmlu_management | 0.8835 |
73
+ | mmlu_marketing | 0.9573 |
74
+ | mmlu_medical_genetics | 0.9700 |
75
+ | mmlu_miscellaneous | 0.9438 |
76
+ | mmlu_moral_disputes | 0.8439 |
77
+ | mmlu_moral_scenarios | 0.7140 |
78
+ | mmlu_nutrition | 0.9118 |
79
+ | mmlu_other | 0.8806 |
80
+ | mmlu_philosophy | 0.8650 |
81
+ | mmlu_prehistory | 0.9105 |
82
+ | mmlu_professional_accounting | 0.8156 |
83
+ | mmlu_professional_law | 0.7073 |
84
+ | mmlu_professional_medicine | 0.9596 |
85
+ | mmlu_professional_psychology | 0.8791 |
86
+ | mmlu_public_relations | 0.7636 |
87
+ | mmlu_security_studies | 0.8204 |
88
+ | mmlu_social_sciences | 0.9129 |
89
+ | mmlu_sociology | 0.9403 |
90
+ | mmlu_stem | 0.8430 |
91
+ | mmlu_us_foreign_policy | 0.9300 |
92
+ | mmlu_virology | 0.5663 |
93
+ | mmlu_world_religions | 0.9006 |
94
+ | piqa | 0.8172 |
95
+
96
+ ## How to Use
97
+
98
+ ### HF Usage
99
+
100
+ **Step 1: Install [AutoRound](https://github.com/intel/auto-round)**
101
+
102
+ ```bash
103
+ pip install auto-round
104
+ ```
105
+
106
+ **Step 2: Load and run the quantized model**
107
+
108
+ ```python
109
+ from transformers import AutoModelForCausalLM, AutoTokenizer
110
+
111
+ model_name = "Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-AutoRound-W4A16-Tuning"
112
+
113
+ # load the tokenizer and the model
114
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
115
+ model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
116
+
117
+ # prepare the model input
118
+ prompt = "Write a quick sort algorithm."
119
+ messages = [{"role": "user", "content": prompt}]
120
+ text = tokenizer.apply_chat_template(
121
+ messages,
122
+ tokenize=False,
123
+ add_generation_prompt=True,
124
+ )
125
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
126
+
127
+ # conduct text completion
128
+ generated_ids = model.generate(**model_inputs, max_new_tokens=512)
129
+ output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()
130
+
131
+ content = tokenizer.decode(output_ids, skip_special_tokens=True)
132
+ print("content:", content)
133
+ ```
134
+
135
+ ### VLLM Usage
136
+
137
+ ```bash
138
+ vllm serve Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-AutoRound-W4A16-Tuning \
139
+ --trust-remote-code \
140
+ --dtype bfloat16 \
141
+ --tensor_parallel_size 1
142
+ ```
143
+
144
+ If you encounter any issues, feel free to open an issue on the [AutoRound GitHub repo](https://github.com/intel/auto-round/issues) or provide feedback on the [Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard).
145
+
146
+ ## Ethical Considerations and Limitations
147
+
148
+ The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
149
+ Therefore, before deploying any applications of the model, developers should perform safety testing.
150
+
151
+ ## Caveats and Recommendations
152
+
153
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
154
+ Here are a couple of useful links to learn more about Intel's AI software:
155
+
156
+ - [Intel Neural Compressor](https://github.com/intel/neural-compressor)
157
+ - [AutoRound](https://github.com/intel/auto-round)
158
+
159
+ ## Disclaimer
160
+
161
+ The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
162
+
163
+ ## Cite
164
+
165
+ ```
166
+ @article{cheng2023optimize,
167
+ title={Optimize weight rounding via signed gradient descent for the quantization of llms},
168
+ author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
169
+ journal={arXiv preprint arXiv:2309.05516},
170
+ year={2023}
171
+ }
172
+ ```
173
+
174
+ [arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
175
+
176
+ ---
177
+
178
+ *This model is part of the [Intel Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard) initiative.*
chat_template.jinja ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set _enable_thinking = false %}
2
+ {%- set preserve_thinking = true %}
3
+ {%- set image_count = namespace(value=0) %}
4
+ {%- set video_count = namespace(value=0) %}
5
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
6
+ {%- if content is string %}
7
+ {{- content }}
8
+ {%- elif content is iterable and content is not mapping %}
9
+ {%- for item in content %}
10
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
11
+ {%- if is_system_content %}
12
+ {{- raise_exception('System message cannot contain images.') }}
13
+ {%- endif %}
14
+ {%- if do_vision_count %}
15
+ {%- set image_count.value = image_count.value + 1 %}
16
+ {%- endif %}
17
+ {%- if add_vision_id is defined and add_vision_id %}
18
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
19
+ {%- endif %}
20
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
21
+ {%- elif 'video' in item or item.type == 'video' %}
22
+ {%- if is_system_content %}
23
+ {{- raise_exception('System message cannot contain videos.') }}
24
+ {%- endif %}
25
+ {%- if do_vision_count %}
26
+ {%- set video_count.value = video_count.value + 1 %}
27
+ {%- endif %}
28
+ {%- if add_vision_id is defined and add_vision_id %}
29
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
30
+ {%- endif %}
31
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
32
+ {%- elif 'text' in item %}
33
+ {{- item.text }}
34
+ {%- else %}
35
+ {{- raise_exception('Unexpected item type in content.') }}
36
+ {%- endif %}
37
+ {%- endfor %}
38
+ {%- elif content is none or content is undefined %}
39
+ {{- '' }}
40
+ {%- else %}
41
+ {{- raise_exception('Unexpected content type.') }}
42
+ {%- endif %}
43
+ {%- endmacro %}
44
+ {%- set ns_flags = namespace(enable_thinking=true) %}
45
+ {%- if enable_thinking is defined %}
46
+ {%- set ns_flags.enable_thinking = enable_thinking %}
47
+ {%- endif %}
48
+ {%- if not messages %}
49
+ {{- raise_exception('No messages provided.') }}
50
+ {%- endif %}
51
+ {%- if tools and tools is iterable and tools is not mapping %}
52
+ {{- '<|im_start|>system\n' }}
53
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
54
+ {%- for tool in tools %}
55
+ {{- "\n" }}
56
+ {{- tool | tojson }}
57
+ {%- endfor %}
58
+ {{- "\n</tools>" }}
59
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
60
+ {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
61
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
62
+ {%- if '<|think_off|>' in content %}
63
+ {%- set ns_flags.enable_thinking = false %}
64
+ {%- set content = content.replace('<|think_off|>', '') %}
65
+ {%- endif %}
66
+ {%- if '<|think_on|>' in content %}
67
+ {%- set ns_flags.enable_thinking = true %}
68
+ {%- set content = content.replace('<|think_on|>', '') %}
69
+ {%- endif %}
70
+ {%- if '<|think_forget|>' in content %}
71
+ {%- set ns_flags.preserve_thinking = false %}
72
+ {%- set content = content.replace('<|think_forget|>', '') %}
73
+ {%- endif %}
74
+ {%- if '<|think_remember|>' in content %}
75
+ {%- set ns_flags.preserve_thinking = true %}
76
+ {%- set content = content.replace('<|think_remember|>', '') %}
77
+ {%- endif %}
78
+ {%- set content = content.strip() %}
79
+ {%- if content %}
80
+ {{- '\n\n' + content }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {{- '<|im_end|>\n' }}
84
+ {%- else %}
85
+ {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
86
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
87
+ {%- if '<|think_off|>' in content %}
88
+ {%- set ns_flags.enable_thinking = false %}
89
+ {%- set content = content.replace('<|think_off|>', '') %}
90
+ {%- endif %}
91
+ {%- if '<|think_on|>' in content %}
92
+ {%- set ns_flags.enable_thinking = true %}
93
+ {%- set content = content.replace('<|think_on|>', '') %}
94
+ {%- endif %}
95
+ {%- if '<|think_forget|>' in content %}
96
+ {%- set ns_flags.preserve_thinking = false %}
97
+ {%- set content = content.replace('<|think_forget|>', '') %}
98
+ {%- endif %}
99
+ {%- if '<|think_remember|>' in content %}
100
+ {%- set ns_flags.preserve_thinking = true %}
101
+ {%- set content = content.replace('<|think_remember|>', '') %}
102
+ {%- endif %}
103
+ {%- set content = content.strip() %}
104
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
108
+ {%- for message in messages[::-1] %}
109
+ {%- set index = (messages|length - 1) - loop.index0 %}
110
+ {%- if ns.multi_step_tool and message.role == "user" %}
111
+ {%- set content = render_content(message.content, false)|trim %}
112
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
113
+ {%- set ns.multi_step_tool = false %}
114
+ {%- set ns.last_query_index = index %}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if ns.multi_step_tool %}
119
+ {{- raise_exception('No user query found in messages.') }}
120
+ {%- endif %}
121
+ {%- for message in messages %}
122
+ {%- set content = render_content(message.content, true)|trim %}
123
+ {%- if '<|think_off|>' in content %}
124
+ {%- set ns_flags.enable_thinking = false %}
125
+ {%- set content = content.replace('<|think_off|>', '') %}
126
+ {%- endif %}
127
+ {%- if '<|think_on|>' in content %}
128
+ {%- set ns_flags.enable_thinking = true %}
129
+ {%- set content = content.replace('<|think_on|>', '') %}
130
+ {%- endif %}
131
+ {%- if '<|think_forget|>' in content %}
132
+ {%- set ns_flags.preserve_thinking = false %}
133
+ {%- set content = content.replace('<|think_forget|>', '') %}
134
+ {%- endif %}
135
+ {%- if '<|think_remember|>' in content %}
136
+ {%- set ns_flags.preserve_thinking = true %}
137
+ {%- set content = content.replace('<|think_remember|>', '') %}
138
+ {%- endif %}
139
+ {%- set content = content.strip() %}
140
+ {%- if message.role == "system" or message.role == "developer" %}
141
+ {%- if not loop.first %}
142
+ {{- raise_exception('System message must be at the beginning.') }}
143
+ {%- endif %}
144
+ {%- elif message.role == "user" %}
145
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
146
+ {%- elif message.role == "assistant" %}
147
+ {%- set reasoning_content = '' %}
148
+ {%- if message.reasoning_content is string %}
149
+ {%- set reasoning_content = message.reasoning_content %}
150
+ {%- else %}
151
+ {%- set has_think_tag = false %}
152
+ {%- set think_end_token = '</think>' %}
153
+ {%- if '</think>' in content %}
154
+ {%- set has_think_tag = true %}
155
+ {%- elif '</thinking>' in content %}
156
+ {%- set has_think_tag = true %}
157
+ {%- set think_end_token = '</thinking>' %}
158
+ {%- elif '<think>' in content %}
159
+ {%- set reasoning_content = content.split('<think>')[-1].lstrip('\n') %}
160
+ {%- set content = '' %}
161
+ {%- endif %}
162
+ {%- if has_think_tag %}
163
+ {%- set reasoning_content = content.split(think_end_token)[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
164
+ {%- set content = content.split(think_end_token)[-1].lstrip('\n') %}
165
+ {%- endif %}
166
+ {%- endif %}
167
+ {%- set reasoning_content = reasoning_content|trim %}
168
+ {%- set show_think = false %}
169
+ {%- if loop.index0 > ns.last_query_index %}
170
+ {%- set show_think = true %}
171
+ {%- elif ns_flags.enable_thinking and (preserve_thinking is undefined or preserve_thinking is true) and reasoning_content|length > 0 %}
172
+ {%- set show_think = true %}
173
+ {%- endif %}
174
+ {%- if show_think %}
175
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
176
+ {%- else %}
177
+ {{- '<|im_start|>' + message.role + '\n' + content }}
178
+ {%- endif %}
179
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
180
+ {%- for tool_call in message.tool_calls %}
181
+ {%- if tool_call.function is defined %}
182
+ {%- set tool_call = tool_call.function %}
183
+ {%- endif %}
184
+ {%- if loop.first %}
185
+ {%- if content|trim %}
186
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
187
+ {%- else %}
188
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
189
+ {%- endif %}
190
+ {%- else %}
191
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
192
+ {%- endif %}
193
+ {%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
194
+ {%- if tool_call.arguments|length > 0 %}
195
+ {%- for args_name in tool_call.arguments %}
196
+ {%- set args_value = tool_call.arguments[args_name] %}
197
+ {{- '<parameter=' + args_name + '>\n' }}
198
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson %}
199
+ {{- args_value }}
200
+ {{- '\n</parameter>\n' }}
201
+ {%- endfor %}
202
+ {%- endif %}
203
+ {%- elif tool_call.arguments is defined and tool_call.arguments is string %}
204
+ {%- if tool_call.arguments|trim|length > 0 %}
205
+ {{- tool_call.arguments }}
206
+ {{- '\n' }}
207
+ {%- endif %}
208
+ {%- endif %}
209
+ {{- '</function>\n</tool_call>' }}
210
+ {%- endfor %}
211
+ {%- endif %}
212
+ {{- '<|im_end|>\n' }}
213
+ {%- elif message.role == "tool" %}
214
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
215
+ {{- '<|im_start|>user' }}
216
+ {%- endif %}
217
+ {{- '\n<tool_response>\n' }}
218
+ {{- content }}
219
+ {{- '\n</tool_response>' }}
220
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
221
+ {{- '<|im_end|>\n' }}
222
+ {%- elif loop.last %}
223
+ {{- '<|im_end|>\n' }}
224
+ {%- endif %}
225
+ {%- else %}
226
+ {{- raise_exception('Unexpected message role.') }}
227
+ {%- endif %}
228
+ {%- endfor %}
229
+ {%- if add_generation_prompt %}
230
+ {{- '<|im_start|>assistant\n' }}
231
+ {%- if ns_flags.enable_thinking is false %}
232
+ {{- '<think>\n\n</think>\n\n' }}
233
+ {%- else %}
234
+ {{- '<think>\n' }}
235
+ {%- endif %}
236
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,2452 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "image_token_id": 248056,
9
+ "language_model_only": false,
10
+ "model_name": "/mnt/w/27B-Qwen3.6-R64-it-vl-HERE-Bradbury-F451-qfx-ss-1x1",
11
+ "model_type": "qwen3_5",
12
+ "pad_token_id": 0,
13
+ "text_config": {
14
+ "attention_bias": false,
15
+ "attention_dropout": 0.0,
16
+ "attn_output_gate": true,
17
+ "bos_token_id": 248044,
18
+ "dtype": "bfloat16",
19
+ "eos_token_id": 248044,
20
+ "full_attention_interval": 4,
21
+ "head_dim": 256,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 5120,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 17408,
26
+ "layer_types": [
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "full_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "full_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "full_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "full_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "full_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "full_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "full_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "full_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "full_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "full_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "full_attention"
91
+ ],
92
+ "linear_conv_kernel_dim": 4,
93
+ "linear_key_head_dim": 128,
94
+ "linear_num_key_heads": 16,
95
+ "linear_num_value_heads": 48,
96
+ "linear_value_head_dim": 128,
97
+ "mamba_ssm_dtype": "float32",
98
+ "max_position_embeddings": 262144,
99
+ "model_type": "qwen3_5_text",
100
+ "mtp_num_hidden_layers": 1,
101
+ "mtp_use_dedicated_embeddings": false,
102
+ "num_attention_heads": 24,
103
+ "num_hidden_layers": 64,
104
+ "num_key_value_heads": 4,
105
+ "output_gate_type": "swish",
106
+ "pad_token_id": null,
107
+ "partial_rotary_factor": 0.25,
108
+ "rms_norm_eps": 1e-06,
109
+ "rope_parameters": {
110
+ "mrope_interleaved": true,
111
+ "mrope_section": [
112
+ 11,
113
+ 11,
114
+ 10
115
+ ],
116
+ "partial_rotary_factor": 0.25,
117
+ "rope_theta": 10000000,
118
+ "rope_type": "default"
119
+ },
120
+ "tie_word_embeddings": false,
121
+ "use_cache": false,
122
+ "vocab_size": 248320
123
+ },
124
+ "tie_word_embeddings": false,
125
+ "transformers_version": "5.12.1",
126
+ "unsloth_version": "2026.7.2",
127
+ "video_token_id": 248057,
128
+ "vision_config": {
129
+ "deepstack_visual_indexes": [],
130
+ "depth": 27,
131
+ "dtype": "bfloat16",
132
+ "hidden_act": "gelu_pytorch_tanh",
133
+ "hidden_size": 1152,
134
+ "in_channels": 3,
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 4304,
137
+ "model_type": "qwen3_5",
138
+ "num_heads": 16,
139
+ "num_position_embeddings": 2304,
140
+ "out_hidden_size": 5120,
141
+ "patch_size": 16,
142
+ "spatial_merge_size": 2,
143
+ "temporal_patch_size": 2
144
+ },
145
+ "vision_end_token_id": 248054,
146
+ "vision_start_token_id": 248053,
147
+ "quantization_config": {
148
+ "quant_method": "auto-round",
149
+ "packing_format": "auto_round:auto_gptq",
150
+ "bits": 4,
151
+ "group_size": 128,
152
+ "sym": true,
153
+ "data_type": "int",
154
+ "iters": 0,
155
+ "model_free": true,
156
+ "autoround_version": "0.14.2",
157
+ "extra_config": {
158
+ "lm_head": {
159
+ "bits": 16,
160
+ "data_type": "float"
161
+ },
162
+ "model.language_model.layers.0.input_layernorm": {
163
+ "bits": 16,
164
+ "data_type": "float"
165
+ },
166
+ "model.language_model.layers.0.linear_attn.norm": {
167
+ "bits": 16,
168
+ "data_type": "float"
169
+ },
170
+ "model.language_model.layers.0.post_attention_layernorm": {
171
+ "bits": 16,
172
+ "data_type": "float"
173
+ },
174
+ "model.language_model.layers.1.input_layernorm": {
175
+ "bits": 16,
176
+ "data_type": "float"
177
+ },
178
+ "model.language_model.layers.1.linear_attn.norm": {
179
+ "bits": 16,
180
+ "data_type": "float"
181
+ },
182
+ "model.language_model.layers.1.post_attention_layernorm": {
183
+ "bits": 16,
184
+ "data_type": "float"
185
+ },
186
+ "model.language_model.layers.10.input_layernorm": {
187
+ "bits": 16,
188
+ "data_type": "float"
189
+ },
190
+ "model.language_model.layers.10.linear_attn.norm": {
191
+ "bits": 16,
192
+ "data_type": "float"
193
+ },
194
+ "model.language_model.layers.10.post_attention_layernorm": {
195
+ "bits": 16,
196
+ "data_type": "float"
197
+ },
198
+ "model.language_model.layers.11.input_layernorm": {
199
+ "bits": 16,
200
+ "data_type": "float"
201
+ },
202
+ "model.language_model.layers.11.post_attention_layernorm": {
203
+ "bits": 16,
204
+ "data_type": "float"
205
+ },
206
+ "model.language_model.layers.11.self_attn.k_norm": {
207
+ "bits": 16,
208
+ "data_type": "float"
209
+ },
210
+ "model.language_model.layers.11.self_attn.q_norm": {
211
+ "bits": 16,
212
+ "data_type": "float"
213
+ },
214
+ "model.language_model.layers.12.input_layernorm": {
215
+ "bits": 16,
216
+ "data_type": "float"
217
+ },
218
+ "model.language_model.layers.12.linear_attn.norm": {
219
+ "bits": 16,
220
+ "data_type": "float"
221
+ },
222
+ "model.language_model.layers.12.post_attention_layernorm": {
223
+ "bits": 16,
224
+ "data_type": "float"
225
+ },
226
+ "model.language_model.layers.13.input_layernorm": {
227
+ "bits": 16,
228
+ "data_type": "float"
229
+ },
230
+ "model.language_model.layers.13.linear_attn.norm": {
231
+ "bits": 16,
232
+ "data_type": "float"
233
+ },
234
+ "model.language_model.layers.13.post_attention_layernorm": {
235
+ "bits": 16,
236
+ "data_type": "float"
237
+ },
238
+ "model.language_model.layers.14.input_layernorm": {
239
+ "bits": 16,
240
+ "data_type": "float"
241
+ },
242
+ "model.language_model.layers.14.linear_attn.norm": {
243
+ "bits": 16,
244
+ "data_type": "float"
245
+ },
246
+ "model.language_model.layers.14.post_attention_layernorm": {
247
+ "bits": 16,
248
+ "data_type": "float"
249
+ },
250
+ "model.language_model.layers.15.input_layernorm": {
251
+ "bits": 16,
252
+ "data_type": "float"
253
+ },
254
+ "model.language_model.layers.15.post_attention_layernorm": {
255
+ "bits": 16,
256
+ "data_type": "float"
257
+ },
258
+ "model.language_model.layers.15.self_attn.k_norm": {
259
+ "bits": 16,
260
+ "data_type": "float"
261
+ },
262
+ "model.language_model.layers.15.self_attn.q_norm": {
263
+ "bits": 16,
264
+ "data_type": "float"
265
+ },
266
+ "model.language_model.layers.16.input_layernorm": {
267
+ "bits": 16,
268
+ "data_type": "float"
269
+ },
270
+ "model.language_model.layers.16.linear_attn.norm": {
271
+ "bits": 16,
272
+ "data_type": "float"
273
+ },
274
+ "model.language_model.layers.16.post_attention_layernorm": {
275
+ "bits": 16,
276
+ "data_type": "float"
277
+ },
278
+ "model.language_model.layers.17.input_layernorm": {
279
+ "bits": 16,
280
+ "data_type": "float"
281
+ },
282
+ "model.language_model.layers.17.linear_attn.norm": {
283
+ "bits": 16,
284
+ "data_type": "float"
285
+ },
286
+ "model.language_model.layers.17.post_attention_layernorm": {
287
+ "bits": 16,
288
+ "data_type": "float"
289
+ },
290
+ "model.language_model.layers.18.input_layernorm": {
291
+ "bits": 16,
292
+ "data_type": "float"
293
+ },
294
+ "model.language_model.layers.18.linear_attn.norm": {
295
+ "bits": 16,
296
+ "data_type": "float"
297
+ },
298
+ "model.language_model.layers.18.post_attention_layernorm": {
299
+ "bits": 16,
300
+ "data_type": "float"
301
+ },
302
+ "model.language_model.layers.19.input_layernorm": {
303
+ "bits": 16,
304
+ "data_type": "float"
305
+ },
306
+ "model.language_model.layers.19.post_attention_layernorm": {
307
+ "bits": 16,
308
+ "data_type": "float"
309
+ },
310
+ "model.language_model.layers.19.self_attn.k_norm": {
311
+ "bits": 16,
312
+ "data_type": "float"
313
+ },
314
+ "model.language_model.layers.19.self_attn.q_norm": {
315
+ "bits": 16,
316
+ "data_type": "float"
317
+ },
318
+ "model.language_model.layers.2.input_layernorm": {
319
+ "bits": 16,
320
+ "data_type": "float"
321
+ },
322
+ "model.language_model.layers.2.linear_attn.norm": {
323
+ "bits": 16,
324
+ "data_type": "float"
325
+ },
326
+ "model.language_model.layers.2.post_attention_layernorm": {
327
+ "bits": 16,
328
+ "data_type": "float"
329
+ },
330
+ "model.language_model.layers.20.input_layernorm": {
331
+ "bits": 16,
332
+ "data_type": "float"
333
+ },
334
+ "model.language_model.layers.20.linear_attn.norm": {
335
+ "bits": 16,
336
+ "data_type": "float"
337
+ },
338
+ "model.language_model.layers.20.post_attention_layernorm": {
339
+ "bits": 16,
340
+ "data_type": "float"
341
+ },
342
+ "model.language_model.layers.21.input_layernorm": {
343
+ "bits": 16,
344
+ "data_type": "float"
345
+ },
346
+ "model.language_model.layers.21.linear_attn.norm": {
347
+ "bits": 16,
348
+ "data_type": "float"
349
+ },
350
+ "model.language_model.layers.21.post_attention_layernorm": {
351
+ "bits": 16,
352
+ "data_type": "float"
353
+ },
354
+ "model.language_model.layers.22.input_layernorm": {
355
+ "bits": 16,
356
+ "data_type": "float"
357
+ },
358
+ "model.language_model.layers.22.linear_attn.norm": {
359
+ "bits": 16,
360
+ "data_type": "float"
361
+ },
362
+ "model.language_model.layers.22.post_attention_layernorm": {
363
+ "bits": 16,
364
+ "data_type": "float"
365
+ },
366
+ "model.language_model.layers.23.input_layernorm": {
367
+ "bits": 16,
368
+ "data_type": "float"
369
+ },
370
+ "model.language_model.layers.23.post_attention_layernorm": {
371
+ "bits": 16,
372
+ "data_type": "float"
373
+ },
374
+ "model.language_model.layers.23.self_attn.k_norm": {
375
+ "bits": 16,
376
+ "data_type": "float"
377
+ },
378
+ "model.language_model.layers.23.self_attn.q_norm": {
379
+ "bits": 16,
380
+ "data_type": "float"
381
+ },
382
+ "model.language_model.layers.24.input_layernorm": {
383
+ "bits": 16,
384
+ "data_type": "float"
385
+ },
386
+ "model.language_model.layers.24.linear_attn.norm": {
387
+ "bits": 16,
388
+ "data_type": "float"
389
+ },
390
+ "model.language_model.layers.24.post_attention_layernorm": {
391
+ "bits": 16,
392
+ "data_type": "float"
393
+ },
394
+ "model.language_model.layers.25.input_layernorm": {
395
+ "bits": 16,
396
+ "data_type": "float"
397
+ },
398
+ "model.language_model.layers.25.linear_attn.norm": {
399
+ "bits": 16,
400
+ "data_type": "float"
401
+ },
402
+ "model.language_model.layers.25.post_attention_layernorm": {
403
+ "bits": 16,
404
+ "data_type": "float"
405
+ },
406
+ "model.language_model.layers.26.input_layernorm": {
407
+ "bits": 16,
408
+ "data_type": "float"
409
+ },
410
+ "model.language_model.layers.26.linear_attn.norm": {
411
+ "bits": 16,
412
+ "data_type": "float"
413
+ },
414
+ "model.language_model.layers.26.post_attention_layernorm": {
415
+ "bits": 16,
416
+ "data_type": "float"
417
+ },
418
+ "model.language_model.layers.27.input_layernorm": {
419
+ "bits": 16,
420
+ "data_type": "float"
421
+ },
422
+ "model.language_model.layers.27.post_attention_layernorm": {
423
+ "bits": 16,
424
+ "data_type": "float"
425
+ },
426
+ "model.language_model.layers.27.self_attn.k_norm": {
427
+ "bits": 16,
428
+ "data_type": "float"
429
+ },
430
+ "model.language_model.layers.27.self_attn.q_norm": {
431
+ "bits": 16,
432
+ "data_type": "float"
433
+ },
434
+ "model.language_model.layers.28.input_layernorm": {
435
+ "bits": 16,
436
+ "data_type": "float"
437
+ },
438
+ "model.language_model.layers.28.linear_attn.norm": {
439
+ "bits": 16,
440
+ "data_type": "float"
441
+ },
442
+ "model.language_model.layers.28.post_attention_layernorm": {
443
+ "bits": 16,
444
+ "data_type": "float"
445
+ },
446
+ "model.language_model.layers.29.input_layernorm": {
447
+ "bits": 16,
448
+ "data_type": "float"
449
+ },
450
+ "model.language_model.layers.29.linear_attn.norm": {
451
+ "bits": 16,
452
+ "data_type": "float"
453
+ },
454
+ "model.language_model.layers.29.post_attention_layernorm": {
455
+ "bits": 16,
456
+ "data_type": "float"
457
+ },
458
+ "model.language_model.layers.3.input_layernorm": {
459
+ "bits": 16,
460
+ "data_type": "float"
461
+ },
462
+ "model.language_model.layers.3.post_attention_layernorm": {
463
+ "bits": 16,
464
+ "data_type": "float"
465
+ },
466
+ "model.language_model.layers.3.self_attn.k_norm": {
467
+ "bits": 16,
468
+ "data_type": "float"
469
+ },
470
+ "model.language_model.layers.3.self_attn.q_norm": {
471
+ "bits": 16,
472
+ "data_type": "float"
473
+ },
474
+ "model.language_model.layers.30.input_layernorm": {
475
+ "bits": 16,
476
+ "data_type": "float"
477
+ },
478
+ "model.language_model.layers.30.linear_attn.norm": {
479
+ "bits": 16,
480
+ "data_type": "float"
481
+ },
482
+ "model.language_model.layers.30.post_attention_layernorm": {
483
+ "bits": 16,
484
+ "data_type": "float"
485
+ },
486
+ "model.language_model.layers.31.input_layernorm": {
487
+ "bits": 16,
488
+ "data_type": "float"
489
+ },
490
+ "model.language_model.layers.31.post_attention_layernorm": {
491
+ "bits": 16,
492
+ "data_type": "float"
493
+ },
494
+ "model.language_model.layers.31.self_attn.k_norm": {
495
+ "bits": 16,
496
+ "data_type": "float"
497
+ },
498
+ "model.language_model.layers.31.self_attn.q_norm": {
499
+ "bits": 16,
500
+ "data_type": "float"
501
+ },
502
+ "model.language_model.layers.32.input_layernorm": {
503
+ "bits": 16,
504
+ "data_type": "float"
505
+ },
506
+ "model.language_model.layers.32.linear_attn.norm": {
507
+ "bits": 16,
508
+ "data_type": "float"
509
+ },
510
+ "model.language_model.layers.32.post_attention_layernorm": {
511
+ "bits": 16,
512
+ "data_type": "float"
513
+ },
514
+ "model.language_model.layers.33.input_layernorm": {
515
+ "bits": 16,
516
+ "data_type": "float"
517
+ },
518
+ "model.language_model.layers.33.linear_attn.norm": {
519
+ "bits": 16,
520
+ "data_type": "float"
521
+ },
522
+ "model.language_model.layers.33.post_attention_layernorm": {
523
+ "bits": 16,
524
+ "data_type": "float"
525
+ },
526
+ "model.language_model.layers.34.input_layernorm": {
527
+ "bits": 16,
528
+ "data_type": "float"
529
+ },
530
+ "model.language_model.layers.34.linear_attn.norm": {
531
+ "bits": 16,
532
+ "data_type": "float"
533
+ },
534
+ "model.language_model.layers.34.post_attention_layernorm": {
535
+ "bits": 16,
536
+ "data_type": "float"
537
+ },
538
+ "model.language_model.layers.35.input_layernorm": {
539
+ "bits": 16,
540
+ "data_type": "float"
541
+ },
542
+ "model.language_model.layers.35.post_attention_layernorm": {
543
+ "bits": 16,
544
+ "data_type": "float"
545
+ },
546
+ "model.language_model.layers.35.self_attn.k_norm": {
547
+ "bits": 16,
548
+ "data_type": "float"
549
+ },
550
+ "model.language_model.layers.35.self_attn.q_norm": {
551
+ "bits": 16,
552
+ "data_type": "float"
553
+ },
554
+ "model.language_model.layers.36.input_layernorm": {
555
+ "bits": 16,
556
+ "data_type": "float"
557
+ },
558
+ "model.language_model.layers.36.linear_attn.norm": {
559
+ "bits": 16,
560
+ "data_type": "float"
561
+ },
562
+ "model.language_model.layers.36.post_attention_layernorm": {
563
+ "bits": 16,
564
+ "data_type": "float"
565
+ },
566
+ "model.language_model.layers.37.input_layernorm": {
567
+ "bits": 16,
568
+ "data_type": "float"
569
+ },
570
+ "model.language_model.layers.37.linear_attn.norm": {
571
+ "bits": 16,
572
+ "data_type": "float"
573
+ },
574
+ "model.language_model.layers.37.post_attention_layernorm": {
575
+ "bits": 16,
576
+ "data_type": "float"
577
+ },
578
+ "model.language_model.layers.38.input_layernorm": {
579
+ "bits": 16,
580
+ "data_type": "float"
581
+ },
582
+ "model.language_model.layers.38.linear_attn.norm": {
583
+ "bits": 16,
584
+ "data_type": "float"
585
+ },
586
+ "model.language_model.layers.38.post_attention_layernorm": {
587
+ "bits": 16,
588
+ "data_type": "float"
589
+ },
590
+ "model.language_model.layers.39.input_layernorm": {
591
+ "bits": 16,
592
+ "data_type": "float"
593
+ },
594
+ "model.language_model.layers.39.post_attention_layernorm": {
595
+ "bits": 16,
596
+ "data_type": "float"
597
+ },
598
+ "model.language_model.layers.39.self_attn.k_norm": {
599
+ "bits": 16,
600
+ "data_type": "float"
601
+ },
602
+ "model.language_model.layers.39.self_attn.q_norm": {
603
+ "bits": 16,
604
+ "data_type": "float"
605
+ },
606
+ "model.language_model.layers.4.input_layernorm": {
607
+ "bits": 16,
608
+ "data_type": "float"
609
+ },
610
+ "model.language_model.layers.4.linear_attn.norm": {
611
+ "bits": 16,
612
+ "data_type": "float"
613
+ },
614
+ "model.language_model.layers.4.post_attention_layernorm": {
615
+ "bits": 16,
616
+ "data_type": "float"
617
+ },
618
+ "model.language_model.layers.40.input_layernorm": {
619
+ "bits": 16,
620
+ "data_type": "float"
621
+ },
622
+ "model.language_model.layers.40.linear_attn.norm": {
623
+ "bits": 16,
624
+ "data_type": "float"
625
+ },
626
+ "model.language_model.layers.40.post_attention_layernorm": {
627
+ "bits": 16,
628
+ "data_type": "float"
629
+ },
630
+ "model.language_model.layers.41.input_layernorm": {
631
+ "bits": 16,
632
+ "data_type": "float"
633
+ },
634
+ "model.language_model.layers.41.linear_attn.norm": {
635
+ "bits": 16,
636
+ "data_type": "float"
637
+ },
638
+ "model.language_model.layers.41.post_attention_layernorm": {
639
+ "bits": 16,
640
+ "data_type": "float"
641
+ },
642
+ "model.language_model.layers.42.input_layernorm": {
643
+ "bits": 16,
644
+ "data_type": "float"
645
+ },
646
+ "model.language_model.layers.42.linear_attn.norm": {
647
+ "bits": 16,
648
+ "data_type": "float"
649
+ },
650
+ "model.language_model.layers.42.post_attention_layernorm": {
651
+ "bits": 16,
652
+ "data_type": "float"
653
+ },
654
+ "model.language_model.layers.43.input_layernorm": {
655
+ "bits": 16,
656
+ "data_type": "float"
657
+ },
658
+ "model.language_model.layers.43.post_attention_layernorm": {
659
+ "bits": 16,
660
+ "data_type": "float"
661
+ },
662
+ "model.language_model.layers.43.self_attn.k_norm": {
663
+ "bits": 16,
664
+ "data_type": "float"
665
+ },
666
+ "model.language_model.layers.43.self_attn.q_norm": {
667
+ "bits": 16,
668
+ "data_type": "float"
669
+ },
670
+ "model.language_model.layers.44.input_layernorm": {
671
+ "bits": 16,
672
+ "data_type": "float"
673
+ },
674
+ "model.language_model.layers.44.linear_attn.norm": {
675
+ "bits": 16,
676
+ "data_type": "float"
677
+ },
678
+ "model.language_model.layers.44.post_attention_layernorm": {
679
+ "bits": 16,
680
+ "data_type": "float"
681
+ },
682
+ "model.language_model.layers.45.input_layernorm": {
683
+ "bits": 16,
684
+ "data_type": "float"
685
+ },
686
+ "model.language_model.layers.45.linear_attn.norm": {
687
+ "bits": 16,
688
+ "data_type": "float"
689
+ },
690
+ "model.language_model.layers.45.post_attention_layernorm": {
691
+ "bits": 16,
692
+ "data_type": "float"
693
+ },
694
+ "model.language_model.layers.46.input_layernorm": {
695
+ "bits": 16,
696
+ "data_type": "float"
697
+ },
698
+ "model.language_model.layers.46.linear_attn.norm": {
699
+ "bits": 16,
700
+ "data_type": "float"
701
+ },
702
+ "model.language_model.layers.46.post_attention_layernorm": {
703
+ "bits": 16,
704
+ "data_type": "float"
705
+ },
706
+ "model.language_model.layers.47.input_layernorm": {
707
+ "bits": 16,
708
+ "data_type": "float"
709
+ },
710
+ "model.language_model.layers.47.post_attention_layernorm": {
711
+ "bits": 16,
712
+ "data_type": "float"
713
+ },
714
+ "model.language_model.layers.47.self_attn.k_norm": {
715
+ "bits": 16,
716
+ "data_type": "float"
717
+ },
718
+ "model.language_model.layers.47.self_attn.q_norm": {
719
+ "bits": 16,
720
+ "data_type": "float"
721
+ },
722
+ "model.language_model.layers.48.input_layernorm": {
723
+ "bits": 16,
724
+ "data_type": "float"
725
+ },
726
+ "model.language_model.layers.48.linear_attn.norm": {
727
+ "bits": 16,
728
+ "data_type": "float"
729
+ },
730
+ "model.language_model.layers.48.post_attention_layernorm": {
731
+ "bits": 16,
732
+ "data_type": "float"
733
+ },
734
+ "model.language_model.layers.49.input_layernorm": {
735
+ "bits": 16,
736
+ "data_type": "float"
737
+ },
738
+ "model.language_model.layers.49.linear_attn.norm": {
739
+ "bits": 16,
740
+ "data_type": "float"
741
+ },
742
+ "model.language_model.layers.49.post_attention_layernorm": {
743
+ "bits": 16,
744
+ "data_type": "float"
745
+ },
746
+ "model.language_model.layers.5.input_layernorm": {
747
+ "bits": 16,
748
+ "data_type": "float"
749
+ },
750
+ "model.language_model.layers.5.linear_attn.norm": {
751
+ "bits": 16,
752
+ "data_type": "float"
753
+ },
754
+ "model.language_model.layers.5.post_attention_layernorm": {
755
+ "bits": 16,
756
+ "data_type": "float"
757
+ },
758
+ "model.language_model.layers.50.input_layernorm": {
759
+ "bits": 16,
760
+ "data_type": "float"
761
+ },
762
+ "model.language_model.layers.50.linear_attn.norm": {
763
+ "bits": 16,
764
+ "data_type": "float"
765
+ },
766
+ "model.language_model.layers.50.post_attention_layernorm": {
767
+ "bits": 16,
768
+ "data_type": "float"
769
+ },
770
+ "model.language_model.layers.51.input_layernorm": {
771
+ "bits": 16,
772
+ "data_type": "float"
773
+ },
774
+ "model.language_model.layers.51.post_attention_layernorm": {
775
+ "bits": 16,
776
+ "data_type": "float"
777
+ },
778
+ "model.language_model.layers.51.self_attn.k_norm": {
779
+ "bits": 16,
780
+ "data_type": "float"
781
+ },
782
+ "model.language_model.layers.51.self_attn.q_norm": {
783
+ "bits": 16,
784
+ "data_type": "float"
785
+ },
786
+ "model.language_model.layers.52.input_layernorm": {
787
+ "bits": 16,
788
+ "data_type": "float"
789
+ },
790
+ "model.language_model.layers.52.linear_attn.norm": {
791
+ "bits": 16,
792
+ "data_type": "float"
793
+ },
794
+ "model.language_model.layers.52.post_attention_layernorm": {
795
+ "bits": 16,
796
+ "data_type": "float"
797
+ },
798
+ "model.language_model.layers.53.input_layernorm": {
799
+ "bits": 16,
800
+ "data_type": "float"
801
+ },
802
+ "model.language_model.layers.53.linear_attn.norm": {
803
+ "bits": 16,
804
+ "data_type": "float"
805
+ },
806
+ "model.language_model.layers.53.post_attention_layernorm": {
807
+ "bits": 16,
808
+ "data_type": "float"
809
+ },
810
+ "model.language_model.layers.54.input_layernorm": {
811
+ "bits": 16,
812
+ "data_type": "float"
813
+ },
814
+ "model.language_model.layers.54.linear_attn.norm": {
815
+ "bits": 16,
816
+ "data_type": "float"
817
+ },
818
+ "model.language_model.layers.54.post_attention_layernorm": {
819
+ "bits": 16,
820
+ "data_type": "float"
821
+ },
822
+ "model.language_model.layers.55.input_layernorm": {
823
+ "bits": 16,
824
+ "data_type": "float"
825
+ },
826
+ "model.language_model.layers.55.post_attention_layernorm": {
827
+ "bits": 16,
828
+ "data_type": "float"
829
+ },
830
+ "model.language_model.layers.55.self_attn.k_norm": {
831
+ "bits": 16,
832
+ "data_type": "float"
833
+ },
834
+ "model.language_model.layers.55.self_attn.q_norm": {
835
+ "bits": 16,
836
+ "data_type": "float"
837
+ },
838
+ "model.language_model.layers.56.input_layernorm": {
839
+ "bits": 16,
840
+ "data_type": "float"
841
+ },
842
+ "model.language_model.layers.56.linear_attn.norm": {
843
+ "bits": 16,
844
+ "data_type": "float"
845
+ },
846
+ "model.language_model.layers.56.post_attention_layernorm": {
847
+ "bits": 16,
848
+ "data_type": "float"
849
+ },
850
+ "model.language_model.layers.57.input_layernorm": {
851
+ "bits": 16,
852
+ "data_type": "float"
853
+ },
854
+ "model.language_model.layers.57.linear_attn.norm": {
855
+ "bits": 16,
856
+ "data_type": "float"
857
+ },
858
+ "model.language_model.layers.57.post_attention_layernorm": {
859
+ "bits": 16,
860
+ "data_type": "float"
861
+ },
862
+ "model.language_model.layers.58.input_layernorm": {
863
+ "bits": 16,
864
+ "data_type": "float"
865
+ },
866
+ "model.language_model.layers.58.linear_attn.norm": {
867
+ "bits": 16,
868
+ "data_type": "float"
869
+ },
870
+ "model.language_model.layers.58.post_attention_layernorm": {
871
+ "bits": 16,
872
+ "data_type": "float"
873
+ },
874
+ "model.language_model.layers.59.input_layernorm": {
875
+ "bits": 16,
876
+ "data_type": "float"
877
+ },
878
+ "model.language_model.layers.59.post_attention_layernorm": {
879
+ "bits": 16,
880
+ "data_type": "float"
881
+ },
882
+ "model.language_model.layers.59.self_attn.k_norm": {
883
+ "bits": 16,
884
+ "data_type": "float"
885
+ },
886
+ "model.language_model.layers.59.self_attn.q_norm": {
887
+ "bits": 16,
888
+ "data_type": "float"
889
+ },
890
+ "model.language_model.layers.6.input_layernorm": {
891
+ "bits": 16,
892
+ "data_type": "float"
893
+ },
894
+ "model.language_model.layers.6.linear_attn.norm": {
895
+ "bits": 16,
896
+ "data_type": "float"
897
+ },
898
+ "model.language_model.layers.6.post_attention_layernorm": {
899
+ "bits": 16,
900
+ "data_type": "float"
901
+ },
902
+ "model.language_model.layers.60.input_layernorm": {
903
+ "bits": 16,
904
+ "data_type": "float"
905
+ },
906
+ "model.language_model.layers.60.linear_attn.norm": {
907
+ "bits": 16,
908
+ "data_type": "float"
909
+ },
910
+ "model.language_model.layers.60.post_attention_layernorm": {
911
+ "bits": 16,
912
+ "data_type": "float"
913
+ },
914
+ "model.language_model.layers.61.input_layernorm": {
915
+ "bits": 16,
916
+ "data_type": "float"
917
+ },
918
+ "model.language_model.layers.61.linear_attn.norm": {
919
+ "bits": 16,
920
+ "data_type": "float"
921
+ },
922
+ "model.language_model.layers.61.post_attention_layernorm": {
923
+ "bits": 16,
924
+ "data_type": "float"
925
+ },
926
+ "model.language_model.layers.62.input_layernorm": {
927
+ "bits": 16,
928
+ "data_type": "float"
929
+ },
930
+ "model.language_model.layers.62.linear_attn.norm": {
931
+ "bits": 16,
932
+ "data_type": "float"
933
+ },
934
+ "model.language_model.layers.62.post_attention_layernorm": {
935
+ "bits": 16,
936
+ "data_type": "float"
937
+ },
938
+ "model.language_model.layers.63.input_layernorm": {
939
+ "bits": 16,
940
+ "data_type": "float"
941
+ },
942
+ "model.language_model.layers.63.post_attention_layernorm": {
943
+ "bits": 16,
944
+ "data_type": "float"
945
+ },
946
+ "model.language_model.layers.63.self_attn.k_norm": {
947
+ "bits": 16,
948
+ "data_type": "float"
949
+ },
950
+ "model.language_model.layers.63.self_attn.q_norm": {
951
+ "bits": 16,
952
+ "data_type": "float"
953
+ },
954
+ "model.language_model.layers.7.input_layernorm": {
955
+ "bits": 16,
956
+ "data_type": "float"
957
+ },
958
+ "model.language_model.layers.7.post_attention_layernorm": {
959
+ "bits": 16,
960
+ "data_type": "float"
961
+ },
962
+ "model.language_model.layers.7.self_attn.k_norm": {
963
+ "bits": 16,
964
+ "data_type": "float"
965
+ },
966
+ "model.language_model.layers.7.self_attn.q_norm": {
967
+ "bits": 16,
968
+ "data_type": "float"
969
+ },
970
+ "model.language_model.layers.8.input_layernorm": {
971
+ "bits": 16,
972
+ "data_type": "float"
973
+ },
974
+ "model.language_model.layers.8.linear_attn.norm": {
975
+ "bits": 16,
976
+ "data_type": "float"
977
+ },
978
+ "model.language_model.layers.8.post_attention_layernorm": {
979
+ "bits": 16,
980
+ "data_type": "float"
981
+ },
982
+ "model.language_model.layers.9.input_layernorm": {
983
+ "bits": 16,
984
+ "data_type": "float"
985
+ },
986
+ "model.language_model.layers.9.linear_attn.norm": {
987
+ "bits": 16,
988
+ "data_type": "float"
989
+ },
990
+ "model.language_model.layers.9.post_attention_layernorm": {
991
+ "bits": 16,
992
+ "data_type": "float"
993
+ },
994
+ "model.language_model.norm": {
995
+ "bits": 16,
996
+ "data_type": "float"
997
+ },
998
+ "model.visual.blocks.0.attn.proj": {
999
+ "bits": 16,
1000
+ "data_type": "float"
1001
+ },
1002
+ "model.visual.blocks.0.attn.qkv": {
1003
+ "bits": 16,
1004
+ "data_type": "float"
1005
+ },
1006
+ "model.visual.blocks.0.mlp.linear_fc1": {
1007
+ "bits": 16,
1008
+ "data_type": "float"
1009
+ },
1010
+ "model.visual.blocks.0.mlp.linear_fc2": {
1011
+ "bits": 16,
1012
+ "data_type": "float"
1013
+ },
1014
+ "model.visual.blocks.0.norm1": {
1015
+ "bits": 16,
1016
+ "data_type": "float"
1017
+ },
1018
+ "model.visual.blocks.0.norm2": {
1019
+ "bits": 16,
1020
+ "data_type": "float"
1021
+ },
1022
+ "model.visual.blocks.1.attn.proj": {
1023
+ "bits": 16,
1024
+ "data_type": "float"
1025
+ },
1026
+ "model.visual.blocks.1.attn.qkv": {
1027
+ "bits": 16,
1028
+ "data_type": "float"
1029
+ },
1030
+ "model.visual.blocks.1.mlp.linear_fc1": {
1031
+ "bits": 16,
1032
+ "data_type": "float"
1033
+ },
1034
+ "model.visual.blocks.1.mlp.linear_fc2": {
1035
+ "bits": 16,
1036
+ "data_type": "float"
1037
+ },
1038
+ "model.visual.blocks.1.norm1": {
1039
+ "bits": 16,
1040
+ "data_type": "float"
1041
+ },
1042
+ "model.visual.blocks.1.norm2": {
1043
+ "bits": 16,
1044
+ "data_type": "float"
1045
+ },
1046
+ "model.visual.blocks.10.attn.proj": {
1047
+ "bits": 16,
1048
+ "data_type": "float"
1049
+ },
1050
+ "model.visual.blocks.10.attn.qkv": {
1051
+ "bits": 16,
1052
+ "data_type": "float"
1053
+ },
1054
+ "model.visual.blocks.10.mlp.linear_fc1": {
1055
+ "bits": 16,
1056
+ "data_type": "float"
1057
+ },
1058
+ "model.visual.blocks.10.mlp.linear_fc2": {
1059
+ "bits": 16,
1060
+ "data_type": "float"
1061
+ },
1062
+ "model.visual.blocks.10.norm1": {
1063
+ "bits": 16,
1064
+ "data_type": "float"
1065
+ },
1066
+ "model.visual.blocks.10.norm2": {
1067
+ "bits": 16,
1068
+ "data_type": "float"
1069
+ },
1070
+ "model.visual.blocks.11.attn.proj": {
1071
+ "bits": 16,
1072
+ "data_type": "float"
1073
+ },
1074
+ "model.visual.blocks.11.attn.qkv": {
1075
+ "bits": 16,
1076
+ "data_type": "float"
1077
+ },
1078
+ "model.visual.blocks.11.mlp.linear_fc1": {
1079
+ "bits": 16,
1080
+ "data_type": "float"
1081
+ },
1082
+ "model.visual.blocks.11.mlp.linear_fc2": {
1083
+ "bits": 16,
1084
+ "data_type": "float"
1085
+ },
1086
+ "model.visual.blocks.11.norm1": {
1087
+ "bits": 16,
1088
+ "data_type": "float"
1089
+ },
1090
+ "model.visual.blocks.11.norm2": {
1091
+ "bits": 16,
1092
+ "data_type": "float"
1093
+ },
1094
+ "model.visual.blocks.12.attn.proj": {
1095
+ "bits": 16,
1096
+ "data_type": "float"
1097
+ },
1098
+ "model.visual.blocks.12.attn.qkv": {
1099
+ "bits": 16,
1100
+ "data_type": "float"
1101
+ },
1102
+ "model.visual.blocks.12.mlp.linear_fc1": {
1103
+ "bits": 16,
1104
+ "data_type": "float"
1105
+ },
1106
+ "model.visual.blocks.12.mlp.linear_fc2": {
1107
+ "bits": 16,
1108
+ "data_type": "float"
1109
+ },
1110
+ "model.visual.blocks.12.norm1": {
1111
+ "bits": 16,
1112
+ "data_type": "float"
1113
+ },
1114
+ "model.visual.blocks.12.norm2": {
1115
+ "bits": 16,
1116
+ "data_type": "float"
1117
+ },
1118
+ "model.visual.blocks.13.attn.proj": {
1119
+ "bits": 16,
1120
+ "data_type": "float"
1121
+ },
1122
+ "model.visual.blocks.13.attn.qkv": {
1123
+ "bits": 16,
1124
+ "data_type": "float"
1125
+ },
1126
+ "model.visual.blocks.13.mlp.linear_fc1": {
1127
+ "bits": 16,
1128
+ "data_type": "float"
1129
+ },
1130
+ "model.visual.blocks.13.mlp.linear_fc2": {
1131
+ "bits": 16,
1132
+ "data_type": "float"
1133
+ },
1134
+ "model.visual.blocks.13.norm1": {
1135
+ "bits": 16,
1136
+ "data_type": "float"
1137
+ },
1138
+ "model.visual.blocks.13.norm2": {
1139
+ "bits": 16,
1140
+ "data_type": "float"
1141
+ },
1142
+ "model.visual.blocks.14.attn.proj": {
1143
+ "bits": 16,
1144
+ "data_type": "float"
1145
+ },
1146
+ "model.visual.blocks.14.attn.qkv": {
1147
+ "bits": 16,
1148
+ "data_type": "float"
1149
+ },
1150
+ "model.visual.blocks.14.mlp.linear_fc1": {
1151
+ "bits": 16,
1152
+ "data_type": "float"
1153
+ },
1154
+ "model.visual.blocks.14.mlp.linear_fc2": {
1155
+ "bits": 16,
1156
+ "data_type": "float"
1157
+ },
1158
+ "model.visual.blocks.14.norm1": {
1159
+ "bits": 16,
1160
+ "data_type": "float"
1161
+ },
1162
+ "model.visual.blocks.14.norm2": {
1163
+ "bits": 16,
1164
+ "data_type": "float"
1165
+ },
1166
+ "model.visual.blocks.15.attn.proj": {
1167
+ "bits": 16,
1168
+ "data_type": "float"
1169
+ },
1170
+ "model.visual.blocks.15.attn.qkv": {
1171
+ "bits": 16,
1172
+ "data_type": "float"
1173
+ },
1174
+ "model.visual.blocks.15.mlp.linear_fc1": {
1175
+ "bits": 16,
1176
+ "data_type": "float"
1177
+ },
1178
+ "model.visual.blocks.15.mlp.linear_fc2": {
1179
+ "bits": 16,
1180
+ "data_type": "float"
1181
+ },
1182
+ "model.visual.blocks.15.norm1": {
1183
+ "bits": 16,
1184
+ "data_type": "float"
1185
+ },
1186
+ "model.visual.blocks.15.norm2": {
1187
+ "bits": 16,
1188
+ "data_type": "float"
1189
+ },
1190
+ "model.visual.blocks.16.attn.proj": {
1191
+ "bits": 16,
1192
+ "data_type": "float"
1193
+ },
1194
+ "model.visual.blocks.16.attn.qkv": {
1195
+ "bits": 16,
1196
+ "data_type": "float"
1197
+ },
1198
+ "model.visual.blocks.16.mlp.linear_fc1": {
1199
+ "bits": 16,
1200
+ "data_type": "float"
1201
+ },
1202
+ "model.visual.blocks.16.mlp.linear_fc2": {
1203
+ "bits": 16,
1204
+ "data_type": "float"
1205
+ },
1206
+ "model.visual.blocks.16.norm1": {
1207
+ "bits": 16,
1208
+ "data_type": "float"
1209
+ },
1210
+ "model.visual.blocks.16.norm2": {
1211
+ "bits": 16,
1212
+ "data_type": "float"
1213
+ },
1214
+ "model.visual.blocks.17.attn.proj": {
1215
+ "bits": 16,
1216
+ "data_type": "float"
1217
+ },
1218
+ "model.visual.blocks.17.attn.qkv": {
1219
+ "bits": 16,
1220
+ "data_type": "float"
1221
+ },
1222
+ "model.visual.blocks.17.mlp.linear_fc1": {
1223
+ "bits": 16,
1224
+ "data_type": "float"
1225
+ },
1226
+ "model.visual.blocks.17.mlp.linear_fc2": {
1227
+ "bits": 16,
1228
+ "data_type": "float"
1229
+ },
1230
+ "model.visual.blocks.17.norm1": {
1231
+ "bits": 16,
1232
+ "data_type": "float"
1233
+ },
1234
+ "model.visual.blocks.17.norm2": {
1235
+ "bits": 16,
1236
+ "data_type": "float"
1237
+ },
1238
+ "model.visual.blocks.18.attn.proj": {
1239
+ "bits": 16,
1240
+ "data_type": "float"
1241
+ },
1242
+ "model.visual.blocks.18.attn.qkv": {
1243
+ "bits": 16,
1244
+ "data_type": "float"
1245
+ },
1246
+ "model.visual.blocks.18.mlp.linear_fc1": {
1247
+ "bits": 16,
1248
+ "data_type": "float"
1249
+ },
1250
+ "model.visual.blocks.18.mlp.linear_fc2": {
1251
+ "bits": 16,
1252
+ "data_type": "float"
1253
+ },
1254
+ "model.visual.blocks.18.norm1": {
1255
+ "bits": 16,
1256
+ "data_type": "float"
1257
+ },
1258
+ "model.visual.blocks.18.norm2": {
1259
+ "bits": 16,
1260
+ "data_type": "float"
1261
+ },
1262
+ "model.visual.blocks.19.attn.proj": {
1263
+ "bits": 16,
1264
+ "data_type": "float"
1265
+ },
1266
+ "model.visual.blocks.19.attn.qkv": {
1267
+ "bits": 16,
1268
+ "data_type": "float"
1269
+ },
1270
+ "model.visual.blocks.19.mlp.linear_fc1": {
1271
+ "bits": 16,
1272
+ "data_type": "float"
1273
+ },
1274
+ "model.visual.blocks.19.mlp.linear_fc2": {
1275
+ "bits": 16,
1276
+ "data_type": "float"
1277
+ },
1278
+ "model.visual.blocks.19.norm1": {
1279
+ "bits": 16,
1280
+ "data_type": "float"
1281
+ },
1282
+ "model.visual.blocks.19.norm2": {
1283
+ "bits": 16,
1284
+ "data_type": "float"
1285
+ },
1286
+ "model.visual.blocks.2.attn.proj": {
1287
+ "bits": 16,
1288
+ "data_type": "float"
1289
+ },
1290
+ "model.visual.blocks.2.attn.qkv": {
1291
+ "bits": 16,
1292
+ "data_type": "float"
1293
+ },
1294
+ "model.visual.blocks.2.mlp.linear_fc1": {
1295
+ "bits": 16,
1296
+ "data_type": "float"
1297
+ },
1298
+ "model.visual.blocks.2.mlp.linear_fc2": {
1299
+ "bits": 16,
1300
+ "data_type": "float"
1301
+ },
1302
+ "model.visual.blocks.2.norm1": {
1303
+ "bits": 16,
1304
+ "data_type": "float"
1305
+ },
1306
+ "model.visual.blocks.2.norm2": {
1307
+ "bits": 16,
1308
+ "data_type": "float"
1309
+ },
1310
+ "model.visual.blocks.20.attn.proj": {
1311
+ "bits": 16,
1312
+ "data_type": "float"
1313
+ },
1314
+ "model.visual.blocks.20.attn.qkv": {
1315
+ "bits": 16,
1316
+ "data_type": "float"
1317
+ },
1318
+ "model.visual.blocks.20.mlp.linear_fc1": {
1319
+ "bits": 16,
1320
+ "data_type": "float"
1321
+ },
1322
+ "model.visual.blocks.20.mlp.linear_fc2": {
1323
+ "bits": 16,
1324
+ "data_type": "float"
1325
+ },
1326
+ "model.visual.blocks.20.norm1": {
1327
+ "bits": 16,
1328
+ "data_type": "float"
1329
+ },
1330
+ "model.visual.blocks.20.norm2": {
1331
+ "bits": 16,
1332
+ "data_type": "float"
1333
+ },
1334
+ "model.visual.blocks.21.attn.proj": {
1335
+ "bits": 16,
1336
+ "data_type": "float"
1337
+ },
1338
+ "model.visual.blocks.21.attn.qkv": {
1339
+ "bits": 16,
1340
+ "data_type": "float"
1341
+ },
1342
+ "model.visual.blocks.21.mlp.linear_fc1": {
1343
+ "bits": 16,
1344
+ "data_type": "float"
1345
+ },
1346
+ "model.visual.blocks.21.mlp.linear_fc2": {
1347
+ "bits": 16,
1348
+ "data_type": "float"
1349
+ },
1350
+ "model.visual.blocks.21.norm1": {
1351
+ "bits": 16,
1352
+ "data_type": "float"
1353
+ },
1354
+ "model.visual.blocks.21.norm2": {
1355
+ "bits": 16,
1356
+ "data_type": "float"
1357
+ },
1358
+ "model.visual.blocks.22.attn.proj": {
1359
+ "bits": 16,
1360
+ "data_type": "float"
1361
+ },
1362
+ "model.visual.blocks.22.attn.qkv": {
1363
+ "bits": 16,
1364
+ "data_type": "float"
1365
+ },
1366
+ "model.visual.blocks.22.mlp.linear_fc1": {
1367
+ "bits": 16,
1368
+ "data_type": "float"
1369
+ },
1370
+ "model.visual.blocks.22.mlp.linear_fc2": {
1371
+ "bits": 16,
1372
+ "data_type": "float"
1373
+ },
1374
+ "model.visual.blocks.22.norm1": {
1375
+ "bits": 16,
1376
+ "data_type": "float"
1377
+ },
1378
+ "model.visual.blocks.22.norm2": {
1379
+ "bits": 16,
1380
+ "data_type": "float"
1381
+ },
1382
+ "model.visual.blocks.23.attn.proj": {
1383
+ "bits": 16,
1384
+ "data_type": "float"
1385
+ },
1386
+ "model.visual.blocks.23.attn.qkv": {
1387
+ "bits": 16,
1388
+ "data_type": "float"
1389
+ },
1390
+ "model.visual.blocks.23.mlp.linear_fc1": {
1391
+ "bits": 16,
1392
+ "data_type": "float"
1393
+ },
1394
+ "model.visual.blocks.23.mlp.linear_fc2": {
1395
+ "bits": 16,
1396
+ "data_type": "float"
1397
+ },
1398
+ "model.visual.blocks.23.norm1": {
1399
+ "bits": 16,
1400
+ "data_type": "float"
1401
+ },
1402
+ "model.visual.blocks.23.norm2": {
1403
+ "bits": 16,
1404
+ "data_type": "float"
1405
+ },
1406
+ "model.visual.blocks.24.attn.proj": {
1407
+ "bits": 16,
1408
+ "data_type": "float"
1409
+ },
1410
+ "model.visual.blocks.24.attn.qkv": {
1411
+ "bits": 16,
1412
+ "data_type": "float"
1413
+ },
1414
+ "model.visual.blocks.24.mlp.linear_fc1": {
1415
+ "bits": 16,
1416
+ "data_type": "float"
1417
+ },
1418
+ "model.visual.blocks.24.mlp.linear_fc2": {
1419
+ "bits": 16,
1420
+ "data_type": "float"
1421
+ },
1422
+ "model.visual.blocks.24.norm1": {
1423
+ "bits": 16,
1424
+ "data_type": "float"
1425
+ },
1426
+ "model.visual.blocks.24.norm2": {
1427
+ "bits": 16,
1428
+ "data_type": "float"
1429
+ },
1430
+ "model.visual.blocks.25.attn.proj": {
1431
+ "bits": 16,
1432
+ "data_type": "float"
1433
+ },
1434
+ "model.visual.blocks.25.attn.qkv": {
1435
+ "bits": 16,
1436
+ "data_type": "float"
1437
+ },
1438
+ "model.visual.blocks.25.mlp.linear_fc1": {
1439
+ "bits": 16,
1440
+ "data_type": "float"
1441
+ },
1442
+ "model.visual.blocks.25.mlp.linear_fc2": {
1443
+ "bits": 16,
1444
+ "data_type": "float"
1445
+ },
1446
+ "model.visual.blocks.25.norm1": {
1447
+ "bits": 16,
1448
+ "data_type": "float"
1449
+ },
1450
+ "model.visual.blocks.25.norm2": {
1451
+ "bits": 16,
1452
+ "data_type": "float"
1453
+ },
1454
+ "model.visual.blocks.26.attn.proj": {
1455
+ "bits": 16,
1456
+ "data_type": "float"
1457
+ },
1458
+ "model.visual.blocks.26.attn.qkv": {
1459
+ "bits": 16,
1460
+ "data_type": "float"
1461
+ },
1462
+ "model.visual.blocks.26.mlp.linear_fc1": {
1463
+ "bits": 16,
1464
+ "data_type": "float"
1465
+ },
1466
+ "model.visual.blocks.26.mlp.linear_fc2": {
1467
+ "bits": 16,
1468
+ "data_type": "float"
1469
+ },
1470
+ "model.visual.blocks.26.norm1": {
1471
+ "bits": 16,
1472
+ "data_type": "float"
1473
+ },
1474
+ "model.visual.blocks.26.norm2": {
1475
+ "bits": 16,
1476
+ "data_type": "float"
1477
+ },
1478
+ "model.visual.blocks.3.attn.proj": {
1479
+ "bits": 16,
1480
+ "data_type": "float"
1481
+ },
1482
+ "model.visual.blocks.3.attn.qkv": {
1483
+ "bits": 16,
1484
+ "data_type": "float"
1485
+ },
1486
+ "model.visual.blocks.3.mlp.linear_fc1": {
1487
+ "bits": 16,
1488
+ "data_type": "float"
1489
+ },
1490
+ "model.visual.blocks.3.mlp.linear_fc2": {
1491
+ "bits": 16,
1492
+ "data_type": "float"
1493
+ },
1494
+ "model.visual.blocks.3.norm1": {
1495
+ "bits": 16,
1496
+ "data_type": "float"
1497
+ },
1498
+ "model.visual.blocks.3.norm2": {
1499
+ "bits": 16,
1500
+ "data_type": "float"
1501
+ },
1502
+ "model.visual.blocks.4.attn.proj": {
1503
+ "bits": 16,
1504
+ "data_type": "float"
1505
+ },
1506
+ "model.visual.blocks.4.attn.qkv": {
1507
+ "bits": 16,
1508
+ "data_type": "float"
1509
+ },
1510
+ "model.visual.blocks.4.mlp.linear_fc1": {
1511
+ "bits": 16,
1512
+ "data_type": "float"
1513
+ },
1514
+ "model.visual.blocks.4.mlp.linear_fc2": {
1515
+ "bits": 16,
1516
+ "data_type": "float"
1517
+ },
1518
+ "model.visual.blocks.4.norm1": {
1519
+ "bits": 16,
1520
+ "data_type": "float"
1521
+ },
1522
+ "model.visual.blocks.4.norm2": {
1523
+ "bits": 16,
1524
+ "data_type": "float"
1525
+ },
1526
+ "model.visual.blocks.5.attn.proj": {
1527
+ "bits": 16,
1528
+ "data_type": "float"
1529
+ },
1530
+ "model.visual.blocks.5.attn.qkv": {
1531
+ "bits": 16,
1532
+ "data_type": "float"
1533
+ },
1534
+ "model.visual.blocks.5.mlp.linear_fc1": {
1535
+ "bits": 16,
1536
+ "data_type": "float"
1537
+ },
1538
+ "model.visual.blocks.5.mlp.linear_fc2": {
1539
+ "bits": 16,
1540
+ "data_type": "float"
1541
+ },
1542
+ "model.visual.blocks.5.norm1": {
1543
+ "bits": 16,
1544
+ "data_type": "float"
1545
+ },
1546
+ "model.visual.blocks.5.norm2": {
1547
+ "bits": 16,
1548
+ "data_type": "float"
1549
+ },
1550
+ "model.visual.blocks.6.attn.proj": {
1551
+ "bits": 16,
1552
+ "data_type": "float"
1553
+ },
1554
+ "model.visual.blocks.6.attn.qkv": {
1555
+ "bits": 16,
1556
+ "data_type": "float"
1557
+ },
1558
+ "model.visual.blocks.6.mlp.linear_fc1": {
1559
+ "bits": 16,
1560
+ "data_type": "float"
1561
+ },
1562
+ "model.visual.blocks.6.mlp.linear_fc2": {
1563
+ "bits": 16,
1564
+ "data_type": "float"
1565
+ },
1566
+ "model.visual.blocks.6.norm1": {
1567
+ "bits": 16,
1568
+ "data_type": "float"
1569
+ },
1570
+ "model.visual.blocks.6.norm2": {
1571
+ "bits": 16,
1572
+ "data_type": "float"
1573
+ },
1574
+ "model.visual.blocks.7.attn.proj": {
1575
+ "bits": 16,
1576
+ "data_type": "float"
1577
+ },
1578
+ "model.visual.blocks.7.attn.qkv": {
1579
+ "bits": 16,
1580
+ "data_type": "float"
1581
+ },
1582
+ "model.visual.blocks.7.mlp.linear_fc1": {
1583
+ "bits": 16,
1584
+ "data_type": "float"
1585
+ },
1586
+ "model.visual.blocks.7.mlp.linear_fc2": {
1587
+ "bits": 16,
1588
+ "data_type": "float"
1589
+ },
1590
+ "model.visual.blocks.7.norm1": {
1591
+ "bits": 16,
1592
+ "data_type": "float"
1593
+ },
1594
+ "model.visual.blocks.7.norm2": {
1595
+ "bits": 16,
1596
+ "data_type": "float"
1597
+ },
1598
+ "model.visual.blocks.8.attn.proj": {
1599
+ "bits": 16,
1600
+ "data_type": "float"
1601
+ },
1602
+ "model.visual.blocks.8.attn.qkv": {
1603
+ "bits": 16,
1604
+ "data_type": "float"
1605
+ },
1606
+ "model.visual.blocks.8.mlp.linear_fc1": {
1607
+ "bits": 16,
1608
+ "data_type": "float"
1609
+ },
1610
+ "model.visual.blocks.8.mlp.linear_fc2": {
1611
+ "bits": 16,
1612
+ "data_type": "float"
1613
+ },
1614
+ "model.visual.blocks.8.norm1": {
1615
+ "bits": 16,
1616
+ "data_type": "float"
1617
+ },
1618
+ "model.visual.blocks.8.norm2": {
1619
+ "bits": 16,
1620
+ "data_type": "float"
1621
+ },
1622
+ "model.visual.blocks.9.attn.proj": {
1623
+ "bits": 16,
1624
+ "data_type": "float"
1625
+ },
1626
+ "model.visual.blocks.9.attn.qkv": {
1627
+ "bits": 16,
1628
+ "data_type": "float"
1629
+ },
1630
+ "model.visual.blocks.9.mlp.linear_fc1": {
1631
+ "bits": 16,
1632
+ "data_type": "float"
1633
+ },
1634
+ "model.visual.blocks.9.mlp.linear_fc2": {
1635
+ "bits": 16,
1636
+ "data_type": "float"
1637
+ },
1638
+ "model.visual.blocks.9.norm1": {
1639
+ "bits": 16,
1640
+ "data_type": "float"
1641
+ },
1642
+ "model.visual.blocks.9.norm2": {
1643
+ "bits": 16,
1644
+ "data_type": "float"
1645
+ },
1646
+ "model.visual.merger.linear_fc1": {
1647
+ "bits": 16,
1648
+ "data_type": "float"
1649
+ },
1650
+ "model.visual.merger.linear_fc2": {
1651
+ "bits": 16,
1652
+ "data_type": "float"
1653
+ },
1654
+ "model.visual.merger.norm": {
1655
+ "bits": 16,
1656
+ "data_type": "float"
1657
+ },
1658
+ "mtp.layers.0.input_layernorm": {
1659
+ "bits": 16,
1660
+ "data_type": "float"
1661
+ },
1662
+ "mtp.layers.0.post_attention_layernorm": {
1663
+ "bits": 16,
1664
+ "data_type": "float"
1665
+ },
1666
+ "mtp.layers.0.self_attn.k_norm": {
1667
+ "bits": 16,
1668
+ "data_type": "float"
1669
+ },
1670
+ "mtp.layers.0.self_attn.q_norm": {
1671
+ "bits": 16,
1672
+ "data_type": "float"
1673
+ },
1674
+ "mtp.norm": {
1675
+ "bits": 16,
1676
+ "data_type": "float"
1677
+ },
1678
+ "mtp.pre_fc_norm_hidden": {
1679
+ "bits": 16,
1680
+ "data_type": "float"
1681
+ },
1682
+ "model.language_model.layers.0.linear_attn.in_proj_a": {
1683
+ "bits": 16,
1684
+ "data_type": "float"
1685
+ },
1686
+ "model.language_model.layers.0.linear_attn.in_proj_b": {
1687
+ "bits": 16,
1688
+ "data_type": "float"
1689
+ },
1690
+ "model.language_model.layers.1.linear_attn.in_proj_a": {
1691
+ "bits": 16,
1692
+ "data_type": "float"
1693
+ },
1694
+ "model.language_model.layers.1.linear_attn.in_proj_b": {
1695
+ "bits": 16,
1696
+ "data_type": "float"
1697
+ },
1698
+ "model.language_model.layers.10.linear_attn.in_proj_a": {
1699
+ "bits": 16,
1700
+ "data_type": "float"
1701
+ },
1702
+ "model.language_model.layers.10.linear_attn.in_proj_b": {
1703
+ "bits": 16,
1704
+ "data_type": "float"
1705
+ },
1706
+ "model.language_model.layers.12.linear_attn.in_proj_a": {
1707
+ "bits": 16,
1708
+ "data_type": "float"
1709
+ },
1710
+ "model.language_model.layers.12.linear_attn.in_proj_b": {
1711
+ "bits": 16,
1712
+ "data_type": "float"
1713
+ },
1714
+ "model.language_model.layers.13.linear_attn.in_proj_a": {
1715
+ "bits": 16,
1716
+ "data_type": "float"
1717
+ },
1718
+ "model.language_model.layers.13.linear_attn.in_proj_b": {
1719
+ "bits": 16,
1720
+ "data_type": "float"
1721
+ },
1722
+ "model.language_model.layers.14.linear_attn.in_proj_a": {
1723
+ "bits": 16,
1724
+ "data_type": "float"
1725
+ },
1726
+ "model.language_model.layers.14.linear_attn.in_proj_b": {
1727
+ "bits": 16,
1728
+ "data_type": "float"
1729
+ },
1730
+ "model.language_model.layers.16.linear_attn.in_proj_a": {
1731
+ "bits": 16,
1732
+ "data_type": "float"
1733
+ },
1734
+ "model.language_model.layers.16.linear_attn.in_proj_b": {
1735
+ "bits": 16,
1736
+ "data_type": "float"
1737
+ },
1738
+ "model.language_model.layers.17.linear_attn.in_proj_a": {
1739
+ "bits": 16,
1740
+ "data_type": "float"
1741
+ },
1742
+ "model.language_model.layers.17.linear_attn.in_proj_b": {
1743
+ "bits": 16,
1744
+ "data_type": "float"
1745
+ },
1746
+ "model.language_model.layers.18.linear_attn.in_proj_a": {
1747
+ "bits": 16,
1748
+ "data_type": "float"
1749
+ },
1750
+ "model.language_model.layers.18.linear_attn.in_proj_b": {
1751
+ "bits": 16,
1752
+ "data_type": "float"
1753
+ },
1754
+ "model.language_model.layers.2.linear_attn.in_proj_a": {
1755
+ "bits": 16,
1756
+ "data_type": "float"
1757
+ },
1758
+ "model.language_model.layers.2.linear_attn.in_proj_b": {
1759
+ "bits": 16,
1760
+ "data_type": "float"
1761
+ },
1762
+ "model.language_model.layers.20.linear_attn.in_proj_a": {
1763
+ "bits": 16,
1764
+ "data_type": "float"
1765
+ },
1766
+ "model.language_model.layers.20.linear_attn.in_proj_b": {
1767
+ "bits": 16,
1768
+ "data_type": "float"
1769
+ },
1770
+ "model.language_model.layers.21.linear_attn.in_proj_a": {
1771
+ "bits": 16,
1772
+ "data_type": "float"
1773
+ },
1774
+ "model.language_model.layers.21.linear_attn.in_proj_b": {
1775
+ "bits": 16,
1776
+ "data_type": "float"
1777
+ },
1778
+ "model.language_model.layers.22.linear_attn.in_proj_a": {
1779
+ "bits": 16,
1780
+ "data_type": "float"
1781
+ },
1782
+ "model.language_model.layers.22.linear_attn.in_proj_b": {
1783
+ "bits": 16,
1784
+ "data_type": "float"
1785
+ },
1786
+ "model.language_model.layers.24.linear_attn.in_proj_a": {
1787
+ "bits": 16,
1788
+ "data_type": "float"
1789
+ },
1790
+ "model.language_model.layers.24.linear_attn.in_proj_b": {
1791
+ "bits": 16,
1792
+ "data_type": "float"
1793
+ },
1794
+ "model.language_model.layers.25.linear_attn.in_proj_a": {
1795
+ "bits": 16,
1796
+ "data_type": "float"
1797
+ },
1798
+ "model.language_model.layers.25.linear_attn.in_proj_b": {
1799
+ "bits": 16,
1800
+ "data_type": "float"
1801
+ },
1802
+ "model.language_model.layers.26.linear_attn.in_proj_a": {
1803
+ "bits": 16,
1804
+ "data_type": "float"
1805
+ },
1806
+ "model.language_model.layers.26.linear_attn.in_proj_b": {
1807
+ "bits": 16,
1808
+ "data_type": "float"
1809
+ },
1810
+ "model.language_model.layers.28.linear_attn.in_proj_a": {
1811
+ "bits": 16,
1812
+ "data_type": "float"
1813
+ },
1814
+ "model.language_model.layers.28.linear_attn.in_proj_b": {
1815
+ "bits": 16,
1816
+ "data_type": "float"
1817
+ },
1818
+ "model.language_model.layers.29.linear_attn.in_proj_a": {
1819
+ "bits": 16,
1820
+ "data_type": "float"
1821
+ },
1822
+ "model.language_model.layers.29.linear_attn.in_proj_b": {
1823
+ "bits": 16,
1824
+ "data_type": "float"
1825
+ },
1826
+ "model.language_model.layers.30.linear_attn.in_proj_a": {
1827
+ "bits": 16,
1828
+ "data_type": "float"
1829
+ },
1830
+ "model.language_model.layers.30.linear_attn.in_proj_b": {
1831
+ "bits": 16,
1832
+ "data_type": "float"
1833
+ },
1834
+ "model.language_model.layers.32.linear_attn.in_proj_a": {
1835
+ "bits": 16,
1836
+ "data_type": "float"
1837
+ },
1838
+ "model.language_model.layers.32.linear_attn.in_proj_b": {
1839
+ "bits": 16,
1840
+ "data_type": "float"
1841
+ },
1842
+ "model.language_model.layers.33.linear_attn.in_proj_a": {
1843
+ "bits": 16,
1844
+ "data_type": "float"
1845
+ },
1846
+ "model.language_model.layers.33.linear_attn.in_proj_b": {
1847
+ "bits": 16,
1848
+ "data_type": "float"
1849
+ },
1850
+ "model.language_model.layers.34.linear_attn.in_proj_a": {
1851
+ "bits": 16,
1852
+ "data_type": "float"
1853
+ },
1854
+ "model.language_model.layers.34.linear_attn.in_proj_b": {
1855
+ "bits": 16,
1856
+ "data_type": "float"
1857
+ },
1858
+ "model.language_model.layers.36.linear_attn.in_proj_a": {
1859
+ "bits": 16,
1860
+ "data_type": "float"
1861
+ },
1862
+ "model.language_model.layers.36.linear_attn.in_proj_b": {
1863
+ "bits": 16,
1864
+ "data_type": "float"
1865
+ },
1866
+ "model.language_model.layers.37.linear_attn.in_proj_a": {
1867
+ "bits": 16,
1868
+ "data_type": "float"
1869
+ },
1870
+ "model.language_model.layers.37.linear_attn.in_proj_b": {
1871
+ "bits": 16,
1872
+ "data_type": "float"
1873
+ },
1874
+ "model.language_model.layers.38.linear_attn.in_proj_a": {
1875
+ "bits": 16,
1876
+ "data_type": "float"
1877
+ },
1878
+ "model.language_model.layers.38.linear_attn.in_proj_b": {
1879
+ "bits": 16,
1880
+ "data_type": "float"
1881
+ },
1882
+ "model.language_model.layers.4.linear_attn.in_proj_a": {
1883
+ "bits": 16,
1884
+ "data_type": "float"
1885
+ },
1886
+ "model.language_model.layers.4.linear_attn.in_proj_b": {
1887
+ "bits": 16,
1888
+ "data_type": "float"
1889
+ },
1890
+ "model.language_model.layers.40.linear_attn.in_proj_a": {
1891
+ "bits": 16,
1892
+ "data_type": "float"
1893
+ },
1894
+ "model.language_model.layers.40.linear_attn.in_proj_b": {
1895
+ "bits": 16,
1896
+ "data_type": "float"
1897
+ },
1898
+ "model.language_model.layers.41.linear_attn.in_proj_a": {
1899
+ "bits": 16,
1900
+ "data_type": "float"
1901
+ },
1902
+ "model.language_model.layers.41.linear_attn.in_proj_b": {
1903
+ "bits": 16,
1904
+ "data_type": "float"
1905
+ },
1906
+ "model.language_model.layers.42.linear_attn.in_proj_a": {
1907
+ "bits": 16,
1908
+ "data_type": "float"
1909
+ },
1910
+ "model.language_model.layers.42.linear_attn.in_proj_b": {
1911
+ "bits": 16,
1912
+ "data_type": "float"
1913
+ },
1914
+ "model.language_model.layers.44.linear_attn.in_proj_a": {
1915
+ "bits": 16,
1916
+ "data_type": "float"
1917
+ },
1918
+ "model.language_model.layers.44.linear_attn.in_proj_b": {
1919
+ "bits": 16,
1920
+ "data_type": "float"
1921
+ },
1922
+ "model.language_model.layers.45.linear_attn.in_proj_a": {
1923
+ "bits": 16,
1924
+ "data_type": "float"
1925
+ },
1926
+ "model.language_model.layers.45.linear_attn.in_proj_b": {
1927
+ "bits": 16,
1928
+ "data_type": "float"
1929
+ },
1930
+ "model.language_model.layers.46.linear_attn.in_proj_a": {
1931
+ "bits": 16,
1932
+ "data_type": "float"
1933
+ },
1934
+ "model.language_model.layers.46.linear_attn.in_proj_b": {
1935
+ "bits": 16,
1936
+ "data_type": "float"
1937
+ },
1938
+ "model.language_model.layers.48.linear_attn.in_proj_a": {
1939
+ "bits": 16,
1940
+ "data_type": "float"
1941
+ },
1942
+ "model.language_model.layers.48.linear_attn.in_proj_b": {
1943
+ "bits": 16,
1944
+ "data_type": "float"
1945
+ },
1946
+ "model.language_model.layers.49.linear_attn.in_proj_a": {
1947
+ "bits": 16,
1948
+ "data_type": "float"
1949
+ },
1950
+ "model.language_model.layers.49.linear_attn.in_proj_b": {
1951
+ "bits": 16,
1952
+ "data_type": "float"
1953
+ },
1954
+ "model.language_model.layers.5.linear_attn.in_proj_a": {
1955
+ "bits": 16,
1956
+ "data_type": "float"
1957
+ },
1958
+ "model.language_model.layers.5.linear_attn.in_proj_b": {
1959
+ "bits": 16,
1960
+ "data_type": "float"
1961
+ },
1962
+ "model.language_model.layers.50.linear_attn.in_proj_a": {
1963
+ "bits": 16,
1964
+ "data_type": "float"
1965
+ },
1966
+ "model.language_model.layers.50.linear_attn.in_proj_b": {
1967
+ "bits": 16,
1968
+ "data_type": "float"
1969
+ },
1970
+ "model.language_model.layers.52.linear_attn.in_proj_a": {
1971
+ "bits": 16,
1972
+ "data_type": "float"
1973
+ },
1974
+ "model.language_model.layers.52.linear_attn.in_proj_b": {
1975
+ "bits": 16,
1976
+ "data_type": "float"
1977
+ },
1978
+ "model.language_model.layers.53.linear_attn.in_proj_a": {
1979
+ "bits": 16,
1980
+ "data_type": "float"
1981
+ },
1982
+ "model.language_model.layers.53.linear_attn.in_proj_b": {
1983
+ "bits": 16,
1984
+ "data_type": "float"
1985
+ },
1986
+ "model.language_model.layers.54.linear_attn.in_proj_a": {
1987
+ "bits": 16,
1988
+ "data_type": "float"
1989
+ },
1990
+ "model.language_model.layers.54.linear_attn.in_proj_b": {
1991
+ "bits": 16,
1992
+ "data_type": "float"
1993
+ },
1994
+ "model.language_model.layers.56.linear_attn.in_proj_a": {
1995
+ "bits": 16,
1996
+ "data_type": "float"
1997
+ },
1998
+ "model.language_model.layers.56.linear_attn.in_proj_b": {
1999
+ "bits": 16,
2000
+ "data_type": "float"
2001
+ },
2002
+ "model.language_model.layers.57.linear_attn.in_proj_a": {
2003
+ "bits": 16,
2004
+ "data_type": "float"
2005
+ },
2006
+ "model.language_model.layers.57.linear_attn.in_proj_b": {
2007
+ "bits": 16,
2008
+ "data_type": "float"
2009
+ },
2010
+ "model.language_model.layers.58.linear_attn.in_proj_a": {
2011
+ "bits": 16,
2012
+ "data_type": "float"
2013
+ },
2014
+ "model.language_model.layers.58.linear_attn.in_proj_b": {
2015
+ "bits": 16,
2016
+ "data_type": "float"
2017
+ },
2018
+ "model.language_model.layers.6.linear_attn.in_proj_a": {
2019
+ "bits": 16,
2020
+ "data_type": "float"
2021
+ },
2022
+ "model.language_model.layers.6.linear_attn.in_proj_b": {
2023
+ "bits": 16,
2024
+ "data_type": "float"
2025
+ },
2026
+ "model.language_model.layers.60.linear_attn.in_proj_a": {
2027
+ "bits": 16,
2028
+ "data_type": "float"
2029
+ },
2030
+ "model.language_model.layers.60.linear_attn.in_proj_b": {
2031
+ "bits": 16,
2032
+ "data_type": "float"
2033
+ },
2034
+ "model.language_model.layers.61.linear_attn.in_proj_a": {
2035
+ "bits": 16,
2036
+ "data_type": "float"
2037
+ },
2038
+ "model.language_model.layers.61.linear_attn.in_proj_b": {
2039
+ "bits": 16,
2040
+ "data_type": "float"
2041
+ },
2042
+ "model.language_model.layers.62.linear_attn.in_proj_a": {
2043
+ "bits": 16,
2044
+ "data_type": "float"
2045
+ },
2046
+ "model.language_model.layers.62.linear_attn.in_proj_b": {
2047
+ "bits": 16,
2048
+ "data_type": "float"
2049
+ },
2050
+ "model.language_model.layers.8.linear_attn.in_proj_a": {
2051
+ "bits": 16,
2052
+ "data_type": "float"
2053
+ },
2054
+ "model.language_model.layers.8.linear_attn.in_proj_b": {
2055
+ "bits": 16,
2056
+ "data_type": "float"
2057
+ },
2058
+ "model.language_model.layers.9.linear_attn.in_proj_a": {
2059
+ "bits": 16,
2060
+ "data_type": "float"
2061
+ },
2062
+ "model.language_model.layers.9.linear_attn.in_proj_b": {
2063
+ "bits": 16,
2064
+ "data_type": "float"
2065
+ },
2066
+ "model.layers.0.linear_attn.in_proj_a": {
2067
+ "bits": 16,
2068
+ "data_type": "float"
2069
+ },
2070
+ "model.layers.0.linear_attn.in_proj_b": {
2071
+ "bits": 16,
2072
+ "data_type": "float"
2073
+ },
2074
+ "model.layers.1.linear_attn.in_proj_a": {
2075
+ "bits": 16,
2076
+ "data_type": "float"
2077
+ },
2078
+ "model.layers.1.linear_attn.in_proj_b": {
2079
+ "bits": 16,
2080
+ "data_type": "float"
2081
+ },
2082
+ "model.layers.10.linear_attn.in_proj_a": {
2083
+ "bits": 16,
2084
+ "data_type": "float"
2085
+ },
2086
+ "model.layers.10.linear_attn.in_proj_b": {
2087
+ "bits": 16,
2088
+ "data_type": "float"
2089
+ },
2090
+ "model.layers.12.linear_attn.in_proj_a": {
2091
+ "bits": 16,
2092
+ "data_type": "float"
2093
+ },
2094
+ "model.layers.12.linear_attn.in_proj_b": {
2095
+ "bits": 16,
2096
+ "data_type": "float"
2097
+ },
2098
+ "model.layers.13.linear_attn.in_proj_a": {
2099
+ "bits": 16,
2100
+ "data_type": "float"
2101
+ },
2102
+ "model.layers.13.linear_attn.in_proj_b": {
2103
+ "bits": 16,
2104
+ "data_type": "float"
2105
+ },
2106
+ "model.layers.14.linear_attn.in_proj_a": {
2107
+ "bits": 16,
2108
+ "data_type": "float"
2109
+ },
2110
+ "model.layers.14.linear_attn.in_proj_b": {
2111
+ "bits": 16,
2112
+ "data_type": "float"
2113
+ },
2114
+ "model.layers.16.linear_attn.in_proj_a": {
2115
+ "bits": 16,
2116
+ "data_type": "float"
2117
+ },
2118
+ "model.layers.16.linear_attn.in_proj_b": {
2119
+ "bits": 16,
2120
+ "data_type": "float"
2121
+ },
2122
+ "model.layers.17.linear_attn.in_proj_a": {
2123
+ "bits": 16,
2124
+ "data_type": "float"
2125
+ },
2126
+ "model.layers.17.linear_attn.in_proj_b": {
2127
+ "bits": 16,
2128
+ "data_type": "float"
2129
+ },
2130
+ "model.layers.18.linear_attn.in_proj_a": {
2131
+ "bits": 16,
2132
+ "data_type": "float"
2133
+ },
2134
+ "model.layers.18.linear_attn.in_proj_b": {
2135
+ "bits": 16,
2136
+ "data_type": "float"
2137
+ },
2138
+ "model.layers.2.linear_attn.in_proj_a": {
2139
+ "bits": 16,
2140
+ "data_type": "float"
2141
+ },
2142
+ "model.layers.2.linear_attn.in_proj_b": {
2143
+ "bits": 16,
2144
+ "data_type": "float"
2145
+ },
2146
+ "model.layers.20.linear_attn.in_proj_a": {
2147
+ "bits": 16,
2148
+ "data_type": "float"
2149
+ },
2150
+ "model.layers.20.linear_attn.in_proj_b": {
2151
+ "bits": 16,
2152
+ "data_type": "float"
2153
+ },
2154
+ "model.layers.21.linear_attn.in_proj_a": {
2155
+ "bits": 16,
2156
+ "data_type": "float"
2157
+ },
2158
+ "model.layers.21.linear_attn.in_proj_b": {
2159
+ "bits": 16,
2160
+ "data_type": "float"
2161
+ },
2162
+ "model.layers.22.linear_attn.in_proj_a": {
2163
+ "bits": 16,
2164
+ "data_type": "float"
2165
+ },
2166
+ "model.layers.22.linear_attn.in_proj_b": {
2167
+ "bits": 16,
2168
+ "data_type": "float"
2169
+ },
2170
+ "model.layers.24.linear_attn.in_proj_a": {
2171
+ "bits": 16,
2172
+ "data_type": "float"
2173
+ },
2174
+ "model.layers.24.linear_attn.in_proj_b": {
2175
+ "bits": 16,
2176
+ "data_type": "float"
2177
+ },
2178
+ "model.layers.25.linear_attn.in_proj_a": {
2179
+ "bits": 16,
2180
+ "data_type": "float"
2181
+ },
2182
+ "model.layers.25.linear_attn.in_proj_b": {
2183
+ "bits": 16,
2184
+ "data_type": "float"
2185
+ },
2186
+ "model.layers.26.linear_attn.in_proj_a": {
2187
+ "bits": 16,
2188
+ "data_type": "float"
2189
+ },
2190
+ "model.layers.26.linear_attn.in_proj_b": {
2191
+ "bits": 16,
2192
+ "data_type": "float"
2193
+ },
2194
+ "model.layers.28.linear_attn.in_proj_a": {
2195
+ "bits": 16,
2196
+ "data_type": "float"
2197
+ },
2198
+ "model.layers.28.linear_attn.in_proj_b": {
2199
+ "bits": 16,
2200
+ "data_type": "float"
2201
+ },
2202
+ "model.layers.29.linear_attn.in_proj_a": {
2203
+ "bits": 16,
2204
+ "data_type": "float"
2205
+ },
2206
+ "model.layers.29.linear_attn.in_proj_b": {
2207
+ "bits": 16,
2208
+ "data_type": "float"
2209
+ },
2210
+ "model.layers.30.linear_attn.in_proj_a": {
2211
+ "bits": 16,
2212
+ "data_type": "float"
2213
+ },
2214
+ "model.layers.30.linear_attn.in_proj_b": {
2215
+ "bits": 16,
2216
+ "data_type": "float"
2217
+ },
2218
+ "model.layers.32.linear_attn.in_proj_a": {
2219
+ "bits": 16,
2220
+ "data_type": "float"
2221
+ },
2222
+ "model.layers.32.linear_attn.in_proj_b": {
2223
+ "bits": 16,
2224
+ "data_type": "float"
2225
+ },
2226
+ "model.layers.33.linear_attn.in_proj_a": {
2227
+ "bits": 16,
2228
+ "data_type": "float"
2229
+ },
2230
+ "model.layers.33.linear_attn.in_proj_b": {
2231
+ "bits": 16,
2232
+ "data_type": "float"
2233
+ },
2234
+ "model.layers.34.linear_attn.in_proj_a": {
2235
+ "bits": 16,
2236
+ "data_type": "float"
2237
+ },
2238
+ "model.layers.34.linear_attn.in_proj_b": {
2239
+ "bits": 16,
2240
+ "data_type": "float"
2241
+ },
2242
+ "model.layers.36.linear_attn.in_proj_a": {
2243
+ "bits": 16,
2244
+ "data_type": "float"
2245
+ },
2246
+ "model.layers.36.linear_attn.in_proj_b": {
2247
+ "bits": 16,
2248
+ "data_type": "float"
2249
+ },
2250
+ "model.layers.37.linear_attn.in_proj_a": {
2251
+ "bits": 16,
2252
+ "data_type": "float"
2253
+ },
2254
+ "model.layers.37.linear_attn.in_proj_b": {
2255
+ "bits": 16,
2256
+ "data_type": "float"
2257
+ },
2258
+ "model.layers.38.linear_attn.in_proj_a": {
2259
+ "bits": 16,
2260
+ "data_type": "float"
2261
+ },
2262
+ "model.layers.38.linear_attn.in_proj_b": {
2263
+ "bits": 16,
2264
+ "data_type": "float"
2265
+ },
2266
+ "model.layers.4.linear_attn.in_proj_a": {
2267
+ "bits": 16,
2268
+ "data_type": "float"
2269
+ },
2270
+ "model.layers.4.linear_attn.in_proj_b": {
2271
+ "bits": 16,
2272
+ "data_type": "float"
2273
+ },
2274
+ "model.layers.40.linear_attn.in_proj_a": {
2275
+ "bits": 16,
2276
+ "data_type": "float"
2277
+ },
2278
+ "model.layers.40.linear_attn.in_proj_b": {
2279
+ "bits": 16,
2280
+ "data_type": "float"
2281
+ },
2282
+ "model.layers.41.linear_attn.in_proj_a": {
2283
+ "bits": 16,
2284
+ "data_type": "float"
2285
+ },
2286
+ "model.layers.41.linear_attn.in_proj_b": {
2287
+ "bits": 16,
2288
+ "data_type": "float"
2289
+ },
2290
+ "model.layers.42.linear_attn.in_proj_a": {
2291
+ "bits": 16,
2292
+ "data_type": "float"
2293
+ },
2294
+ "model.layers.42.linear_attn.in_proj_b": {
2295
+ "bits": 16,
2296
+ "data_type": "float"
2297
+ },
2298
+ "model.layers.44.linear_attn.in_proj_a": {
2299
+ "bits": 16,
2300
+ "data_type": "float"
2301
+ },
2302
+ "model.layers.44.linear_attn.in_proj_b": {
2303
+ "bits": 16,
2304
+ "data_type": "float"
2305
+ },
2306
+ "model.layers.45.linear_attn.in_proj_a": {
2307
+ "bits": 16,
2308
+ "data_type": "float"
2309
+ },
2310
+ "model.layers.45.linear_attn.in_proj_b": {
2311
+ "bits": 16,
2312
+ "data_type": "float"
2313
+ },
2314
+ "model.layers.46.linear_attn.in_proj_a": {
2315
+ "bits": 16,
2316
+ "data_type": "float"
2317
+ },
2318
+ "model.layers.46.linear_attn.in_proj_b": {
2319
+ "bits": 16,
2320
+ "data_type": "float"
2321
+ },
2322
+ "model.layers.48.linear_attn.in_proj_a": {
2323
+ "bits": 16,
2324
+ "data_type": "float"
2325
+ },
2326
+ "model.layers.48.linear_attn.in_proj_b": {
2327
+ "bits": 16,
2328
+ "data_type": "float"
2329
+ },
2330
+ "model.layers.49.linear_attn.in_proj_a": {
2331
+ "bits": 16,
2332
+ "data_type": "float"
2333
+ },
2334
+ "model.layers.49.linear_attn.in_proj_b": {
2335
+ "bits": 16,
2336
+ "data_type": "float"
2337
+ },
2338
+ "model.layers.5.linear_attn.in_proj_a": {
2339
+ "bits": 16,
2340
+ "data_type": "float"
2341
+ },
2342
+ "model.layers.5.linear_attn.in_proj_b": {
2343
+ "bits": 16,
2344
+ "data_type": "float"
2345
+ },
2346
+ "model.layers.50.linear_attn.in_proj_a": {
2347
+ "bits": 16,
2348
+ "data_type": "float"
2349
+ },
2350
+ "model.layers.50.linear_attn.in_proj_b": {
2351
+ "bits": 16,
2352
+ "data_type": "float"
2353
+ },
2354
+ "model.layers.52.linear_attn.in_proj_a": {
2355
+ "bits": 16,
2356
+ "data_type": "float"
2357
+ },
2358
+ "model.layers.52.linear_attn.in_proj_b": {
2359
+ "bits": 16,
2360
+ "data_type": "float"
2361
+ },
2362
+ "model.layers.53.linear_attn.in_proj_a": {
2363
+ "bits": 16,
2364
+ "data_type": "float"
2365
+ },
2366
+ "model.layers.53.linear_attn.in_proj_b": {
2367
+ "bits": 16,
2368
+ "data_type": "float"
2369
+ },
2370
+ "model.layers.54.linear_attn.in_proj_a": {
2371
+ "bits": 16,
2372
+ "data_type": "float"
2373
+ },
2374
+ "model.layers.54.linear_attn.in_proj_b": {
2375
+ "bits": 16,
2376
+ "data_type": "float"
2377
+ },
2378
+ "model.layers.56.linear_attn.in_proj_a": {
2379
+ "bits": 16,
2380
+ "data_type": "float"
2381
+ },
2382
+ "model.layers.56.linear_attn.in_proj_b": {
2383
+ "bits": 16,
2384
+ "data_type": "float"
2385
+ },
2386
+ "model.layers.57.linear_attn.in_proj_a": {
2387
+ "bits": 16,
2388
+ "data_type": "float"
2389
+ },
2390
+ "model.layers.57.linear_attn.in_proj_b": {
2391
+ "bits": 16,
2392
+ "data_type": "float"
2393
+ },
2394
+ "model.layers.58.linear_attn.in_proj_a": {
2395
+ "bits": 16,
2396
+ "data_type": "float"
2397
+ },
2398
+ "model.layers.58.linear_attn.in_proj_b": {
2399
+ "bits": 16,
2400
+ "data_type": "float"
2401
+ },
2402
+ "model.layers.6.linear_attn.in_proj_a": {
2403
+ "bits": 16,
2404
+ "data_type": "float"
2405
+ },
2406
+ "model.layers.6.linear_attn.in_proj_b": {
2407
+ "bits": 16,
2408
+ "data_type": "float"
2409
+ },
2410
+ "model.layers.60.linear_attn.in_proj_a": {
2411
+ "bits": 16,
2412
+ "data_type": "float"
2413
+ },
2414
+ "model.layers.60.linear_attn.in_proj_b": {
2415
+ "bits": 16,
2416
+ "data_type": "float"
2417
+ },
2418
+ "model.layers.61.linear_attn.in_proj_a": {
2419
+ "bits": 16,
2420
+ "data_type": "float"
2421
+ },
2422
+ "model.layers.61.linear_attn.in_proj_b": {
2423
+ "bits": 16,
2424
+ "data_type": "float"
2425
+ },
2426
+ "model.layers.62.linear_attn.in_proj_a": {
2427
+ "bits": 16,
2428
+ "data_type": "float"
2429
+ },
2430
+ "model.layers.62.linear_attn.in_proj_b": {
2431
+ "bits": 16,
2432
+ "data_type": "float"
2433
+ },
2434
+ "model.layers.8.linear_attn.in_proj_a": {
2435
+ "bits": 16,
2436
+ "data_type": "float"
2437
+ },
2438
+ "model.layers.8.linear_attn.in_proj_b": {
2439
+ "bits": 16,
2440
+ "data_type": "float"
2441
+ },
2442
+ "model.layers.9.linear_attn.in_proj_a": {
2443
+ "bits": 16,
2444
+ "data_type": "float"
2445
+ },
2446
+ "model.layers.9.linear_attn.in_proj_b": {
2447
+ "bits": 16,
2448
+ "data_type": "float"
2449
+ }
2450
+ }
2451
+ }
2452
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.9.0"
13
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: Qwen3.6-27B-Architect-Polaris2-Fable-B
3
+ parameters:
4
+ weight: 1.4
5
+ - model: Qwen3.6-27B-Architect-Polaris-Fable-F451
6
+ parameters:
7
+ weight: 0.6
8
+ merge_method: nuslerp
9
+ dtype: bfloat16
10
+ name: Qwen3.6-27B-Architect-Polaris2-Fable-B-F451
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d1cb5cf0dfab29aac8227b0e273d7d624fdfc3c9be2ae71e0f7d10847693ea
3
+ size 2542796896
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20eeb33c0fe8bc1efa6613256f448669711b44ed39df1edc1c510e39cbe6f60
3
+ size 3142596016
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2b632384f9a51a8c1f1211e928c939d1dceecfdbddca40c7a735a8f9aa9a6d
3
+ size 1293850648
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b59e41ed9e71a1a7209f67b48cdf7448eb044beb5432dba33f6d02ade210fd
3
+ size 1285697392
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3527264439eb8c77dddbbf1b3e7669695ab7de29680acfc9c9f22f1afebb3bee
3
+ size 1293850648
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62bdae2ea2f4e52b16379a36ffcfab2e03c2d19c2aa4ff49031c80164186579
3
+ size 1279185136
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bc3f8cc0f2c9d0adf5a9077594bc571f10d09e1099c06d719ebd877d4a6bfc
3
+ size 1293850624
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03552ae5c9a81dae9c92615a221f29a850d1eee06d05817e1a753035d2a9600
3
+ size 1285697416
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cdd1b12c74873585732f5233a2cae42a683fec0fa0a6a7903db9a9cba43ed4
3
+ size 1293850632
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23792a64fa20638ef0385b9573a9bd4c0082f30d417e77925fa139160b7c503
3
+ size 1285697416
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161c82b90e08781436d7d105080acc698f037532c56d17f547452638022f248a
3
+ size 1279164400
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d17a76fa5421943a40a11de50136b15dce4354400cdb71ce2cdd6e7d248eefd
3
+ size 1642849368
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
quantization_config.json ADDED
@@ -0,0 +1,1537 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quant_method": "auto-round",
3
+ "packing_format": "auto_round:auto_gptq",
4
+ "bits": 4,
5
+ "group_size": 128,
6
+ "sym": true,
7
+ "data_type": "int",
8
+ "iters": 0,
9
+ "model_free": true,
10
+ "autoround_version": "0.14.2",
11
+ "extra_config": {
12
+ "lm_head": {
13
+ "bits": 16,
14
+ "data_type": "float"
15
+ },
16
+ "model.language_model.layers.0.input_layernorm": {
17
+ "bits": 16,
18
+ "data_type": "float"
19
+ },
20
+ "model.language_model.layers.0.linear_attn.norm": {
21
+ "bits": 16,
22
+ "data_type": "float"
23
+ },
24
+ "model.language_model.layers.0.post_attention_layernorm": {
25
+ "bits": 16,
26
+ "data_type": "float"
27
+ },
28
+ "model.language_model.layers.1.input_layernorm": {
29
+ "bits": 16,
30
+ "data_type": "float"
31
+ },
32
+ "model.language_model.layers.1.linear_attn.norm": {
33
+ "bits": 16,
34
+ "data_type": "float"
35
+ },
36
+ "model.language_model.layers.1.post_attention_layernorm": {
37
+ "bits": 16,
38
+ "data_type": "float"
39
+ },
40
+ "model.language_model.layers.10.input_layernorm": {
41
+ "bits": 16,
42
+ "data_type": "float"
43
+ },
44
+ "model.language_model.layers.10.linear_attn.norm": {
45
+ "bits": 16,
46
+ "data_type": "float"
47
+ },
48
+ "model.language_model.layers.10.post_attention_layernorm": {
49
+ "bits": 16,
50
+ "data_type": "float"
51
+ },
52
+ "model.language_model.layers.11.input_layernorm": {
53
+ "bits": 16,
54
+ "data_type": "float"
55
+ },
56
+ "model.language_model.layers.11.post_attention_layernorm": {
57
+ "bits": 16,
58
+ "data_type": "float"
59
+ },
60
+ "model.language_model.layers.11.self_attn.k_norm": {
61
+ "bits": 16,
62
+ "data_type": "float"
63
+ },
64
+ "model.language_model.layers.11.self_attn.q_norm": {
65
+ "bits": 16,
66
+ "data_type": "float"
67
+ },
68
+ "model.language_model.layers.12.input_layernorm": {
69
+ "bits": 16,
70
+ "data_type": "float"
71
+ },
72
+ "model.language_model.layers.12.linear_attn.norm": {
73
+ "bits": 16,
74
+ "data_type": "float"
75
+ },
76
+ "model.language_model.layers.12.post_attention_layernorm": {
77
+ "bits": 16,
78
+ "data_type": "float"
79
+ },
80
+ "model.language_model.layers.13.input_layernorm": {
81
+ "bits": 16,
82
+ "data_type": "float"
83
+ },
84
+ "model.language_model.layers.13.linear_attn.norm": {
85
+ "bits": 16,
86
+ "data_type": "float"
87
+ },
88
+ "model.language_model.layers.13.post_attention_layernorm": {
89
+ "bits": 16,
90
+ "data_type": "float"
91
+ },
92
+ "model.language_model.layers.14.input_layernorm": {
93
+ "bits": 16,
94
+ "data_type": "float"
95
+ },
96
+ "model.language_model.layers.14.linear_attn.norm": {
97
+ "bits": 16,
98
+ "data_type": "float"
99
+ },
100
+ "model.language_model.layers.14.post_attention_layernorm": {
101
+ "bits": 16,
102
+ "data_type": "float"
103
+ },
104
+ "model.language_model.layers.15.input_layernorm": {
105
+ "bits": 16,
106
+ "data_type": "float"
107
+ },
108
+ "model.language_model.layers.15.post_attention_layernorm": {
109
+ "bits": 16,
110
+ "data_type": "float"
111
+ },
112
+ "model.language_model.layers.15.self_attn.k_norm": {
113
+ "bits": 16,
114
+ "data_type": "float"
115
+ },
116
+ "model.language_model.layers.15.self_attn.q_norm": {
117
+ "bits": 16,
118
+ "data_type": "float"
119
+ },
120
+ "model.language_model.layers.16.input_layernorm": {
121
+ "bits": 16,
122
+ "data_type": "float"
123
+ },
124
+ "model.language_model.layers.16.linear_attn.norm": {
125
+ "bits": 16,
126
+ "data_type": "float"
127
+ },
128
+ "model.language_model.layers.16.post_attention_layernorm": {
129
+ "bits": 16,
130
+ "data_type": "float"
131
+ },
132
+ "model.language_model.layers.17.input_layernorm": {
133
+ "bits": 16,
134
+ "data_type": "float"
135
+ },
136
+ "model.language_model.layers.17.linear_attn.norm": {
137
+ "bits": 16,
138
+ "data_type": "float"
139
+ },
140
+ "model.language_model.layers.17.post_attention_layernorm": {
141
+ "bits": 16,
142
+ "data_type": "float"
143
+ },
144
+ "model.language_model.layers.18.input_layernorm": {
145
+ "bits": 16,
146
+ "data_type": "float"
147
+ },
148
+ "model.language_model.layers.18.linear_attn.norm": {
149
+ "bits": 16,
150
+ "data_type": "float"
151
+ },
152
+ "model.language_model.layers.18.post_attention_layernorm": {
153
+ "bits": 16,
154
+ "data_type": "float"
155
+ },
156
+ "model.language_model.layers.19.input_layernorm": {
157
+ "bits": 16,
158
+ "data_type": "float"
159
+ },
160
+ "model.language_model.layers.19.post_attention_layernorm": {
161
+ "bits": 16,
162
+ "data_type": "float"
163
+ },
164
+ "model.language_model.layers.19.self_attn.k_norm": {
165
+ "bits": 16,
166
+ "data_type": "float"
167
+ },
168
+ "model.language_model.layers.19.self_attn.q_norm": {
169
+ "bits": 16,
170
+ "data_type": "float"
171
+ },
172
+ "model.language_model.layers.2.input_layernorm": {
173
+ "bits": 16,
174
+ "data_type": "float"
175
+ },
176
+ "model.language_model.layers.2.linear_attn.norm": {
177
+ "bits": 16,
178
+ "data_type": "float"
179
+ },
180
+ "model.language_model.layers.2.post_attention_layernorm": {
181
+ "bits": 16,
182
+ "data_type": "float"
183
+ },
184
+ "model.language_model.layers.20.input_layernorm": {
185
+ "bits": 16,
186
+ "data_type": "float"
187
+ },
188
+ "model.language_model.layers.20.linear_attn.norm": {
189
+ "bits": 16,
190
+ "data_type": "float"
191
+ },
192
+ "model.language_model.layers.20.post_attention_layernorm": {
193
+ "bits": 16,
194
+ "data_type": "float"
195
+ },
196
+ "model.language_model.layers.21.input_layernorm": {
197
+ "bits": 16,
198
+ "data_type": "float"
199
+ },
200
+ "model.language_model.layers.21.linear_attn.norm": {
201
+ "bits": 16,
202
+ "data_type": "float"
203
+ },
204
+ "model.language_model.layers.21.post_attention_layernorm": {
205
+ "bits": 16,
206
+ "data_type": "float"
207
+ },
208
+ "model.language_model.layers.22.input_layernorm": {
209
+ "bits": 16,
210
+ "data_type": "float"
211
+ },
212
+ "model.language_model.layers.22.linear_attn.norm": {
213
+ "bits": 16,
214
+ "data_type": "float"
215
+ },
216
+ "model.language_model.layers.22.post_attention_layernorm": {
217
+ "bits": 16,
218
+ "data_type": "float"
219
+ },
220
+ "model.language_model.layers.23.input_layernorm": {
221
+ "bits": 16,
222
+ "data_type": "float"
223
+ },
224
+ "model.language_model.layers.23.post_attention_layernorm": {
225
+ "bits": 16,
226
+ "data_type": "float"
227
+ },
228
+ "model.language_model.layers.23.self_attn.k_norm": {
229
+ "bits": 16,
230
+ "data_type": "float"
231
+ },
232
+ "model.language_model.layers.23.self_attn.q_norm": {
233
+ "bits": 16,
234
+ "data_type": "float"
235
+ },
236
+ "model.language_model.layers.24.input_layernorm": {
237
+ "bits": 16,
238
+ "data_type": "float"
239
+ },
240
+ "model.language_model.layers.24.linear_attn.norm": {
241
+ "bits": 16,
242
+ "data_type": "float"
243
+ },
244
+ "model.language_model.layers.24.post_attention_layernorm": {
245
+ "bits": 16,
246
+ "data_type": "float"
247
+ },
248
+ "model.language_model.layers.25.input_layernorm": {
249
+ "bits": 16,
250
+ "data_type": "float"
251
+ },
252
+ "model.language_model.layers.25.linear_attn.norm": {
253
+ "bits": 16,
254
+ "data_type": "float"
255
+ },
256
+ "model.language_model.layers.25.post_attention_layernorm": {
257
+ "bits": 16,
258
+ "data_type": "float"
259
+ },
260
+ "model.language_model.layers.26.input_layernorm": {
261
+ "bits": 16,
262
+ "data_type": "float"
263
+ },
264
+ "model.language_model.layers.26.linear_attn.norm": {
265
+ "bits": 16,
266
+ "data_type": "float"
267
+ },
268
+ "model.language_model.layers.26.post_attention_layernorm": {
269
+ "bits": 16,
270
+ "data_type": "float"
271
+ },
272
+ "model.language_model.layers.27.input_layernorm": {
273
+ "bits": 16,
274
+ "data_type": "float"
275
+ },
276
+ "model.language_model.layers.27.post_attention_layernorm": {
277
+ "bits": 16,
278
+ "data_type": "float"
279
+ },
280
+ "model.language_model.layers.27.self_attn.k_norm": {
281
+ "bits": 16,
282
+ "data_type": "float"
283
+ },
284
+ "model.language_model.layers.27.self_attn.q_norm": {
285
+ "bits": 16,
286
+ "data_type": "float"
287
+ },
288
+ "model.language_model.layers.28.input_layernorm": {
289
+ "bits": 16,
290
+ "data_type": "float"
291
+ },
292
+ "model.language_model.layers.28.linear_attn.norm": {
293
+ "bits": 16,
294
+ "data_type": "float"
295
+ },
296
+ "model.language_model.layers.28.post_attention_layernorm": {
297
+ "bits": 16,
298
+ "data_type": "float"
299
+ },
300
+ "model.language_model.layers.29.input_layernorm": {
301
+ "bits": 16,
302
+ "data_type": "float"
303
+ },
304
+ "model.language_model.layers.29.linear_attn.norm": {
305
+ "bits": 16,
306
+ "data_type": "float"
307
+ },
308
+ "model.language_model.layers.29.post_attention_layernorm": {
309
+ "bits": 16,
310
+ "data_type": "float"
311
+ },
312
+ "model.language_model.layers.3.input_layernorm": {
313
+ "bits": 16,
314
+ "data_type": "float"
315
+ },
316
+ "model.language_model.layers.3.post_attention_layernorm": {
317
+ "bits": 16,
318
+ "data_type": "float"
319
+ },
320
+ "model.language_model.layers.3.self_attn.k_norm": {
321
+ "bits": 16,
322
+ "data_type": "float"
323
+ },
324
+ "model.language_model.layers.3.self_attn.q_norm": {
325
+ "bits": 16,
326
+ "data_type": "float"
327
+ },
328
+ "model.language_model.layers.30.input_layernorm": {
329
+ "bits": 16,
330
+ "data_type": "float"
331
+ },
332
+ "model.language_model.layers.30.linear_attn.norm": {
333
+ "bits": 16,
334
+ "data_type": "float"
335
+ },
336
+ "model.language_model.layers.30.post_attention_layernorm": {
337
+ "bits": 16,
338
+ "data_type": "float"
339
+ },
340
+ "model.language_model.layers.31.input_layernorm": {
341
+ "bits": 16,
342
+ "data_type": "float"
343
+ },
344
+ "model.language_model.layers.31.post_attention_layernorm": {
345
+ "bits": 16,
346
+ "data_type": "float"
347
+ },
348
+ "model.language_model.layers.31.self_attn.k_norm": {
349
+ "bits": 16,
350
+ "data_type": "float"
351
+ },
352
+ "model.language_model.layers.31.self_attn.q_norm": {
353
+ "bits": 16,
354
+ "data_type": "float"
355
+ },
356
+ "model.language_model.layers.32.input_layernorm": {
357
+ "bits": 16,
358
+ "data_type": "float"
359
+ },
360
+ "model.language_model.layers.32.linear_attn.norm": {
361
+ "bits": 16,
362
+ "data_type": "float"
363
+ },
364
+ "model.language_model.layers.32.post_attention_layernorm": {
365
+ "bits": 16,
366
+ "data_type": "float"
367
+ },
368
+ "model.language_model.layers.33.input_layernorm": {
369
+ "bits": 16,
370
+ "data_type": "float"
371
+ },
372
+ "model.language_model.layers.33.linear_attn.norm": {
373
+ "bits": 16,
374
+ "data_type": "float"
375
+ },
376
+ "model.language_model.layers.33.post_attention_layernorm": {
377
+ "bits": 16,
378
+ "data_type": "float"
379
+ },
380
+ "model.language_model.layers.34.input_layernorm": {
381
+ "bits": 16,
382
+ "data_type": "float"
383
+ },
384
+ "model.language_model.layers.34.linear_attn.norm": {
385
+ "bits": 16,
386
+ "data_type": "float"
387
+ },
388
+ "model.language_model.layers.34.post_attention_layernorm": {
389
+ "bits": 16,
390
+ "data_type": "float"
391
+ },
392
+ "model.language_model.layers.35.input_layernorm": {
393
+ "bits": 16,
394
+ "data_type": "float"
395
+ },
396
+ "model.language_model.layers.35.post_attention_layernorm": {
397
+ "bits": 16,
398
+ "data_type": "float"
399
+ },
400
+ "model.language_model.layers.35.self_attn.k_norm": {
401
+ "bits": 16,
402
+ "data_type": "float"
403
+ },
404
+ "model.language_model.layers.35.self_attn.q_norm": {
405
+ "bits": 16,
406
+ "data_type": "float"
407
+ },
408
+ "model.language_model.layers.36.input_layernorm": {
409
+ "bits": 16,
410
+ "data_type": "float"
411
+ },
412
+ "model.language_model.layers.36.linear_attn.norm": {
413
+ "bits": 16,
414
+ "data_type": "float"
415
+ },
416
+ "model.language_model.layers.36.post_attention_layernorm": {
417
+ "bits": 16,
418
+ "data_type": "float"
419
+ },
420
+ "model.language_model.layers.37.input_layernorm": {
421
+ "bits": 16,
422
+ "data_type": "float"
423
+ },
424
+ "model.language_model.layers.37.linear_attn.norm": {
425
+ "bits": 16,
426
+ "data_type": "float"
427
+ },
428
+ "model.language_model.layers.37.post_attention_layernorm": {
429
+ "bits": 16,
430
+ "data_type": "float"
431
+ },
432
+ "model.language_model.layers.38.input_layernorm": {
433
+ "bits": 16,
434
+ "data_type": "float"
435
+ },
436
+ "model.language_model.layers.38.linear_attn.norm": {
437
+ "bits": 16,
438
+ "data_type": "float"
439
+ },
440
+ "model.language_model.layers.38.post_attention_layernorm": {
441
+ "bits": 16,
442
+ "data_type": "float"
443
+ },
444
+ "model.language_model.layers.39.input_layernorm": {
445
+ "bits": 16,
446
+ "data_type": "float"
447
+ },
448
+ "model.language_model.layers.39.post_attention_layernorm": {
449
+ "bits": 16,
450
+ "data_type": "float"
451
+ },
452
+ "model.language_model.layers.39.self_attn.k_norm": {
453
+ "bits": 16,
454
+ "data_type": "float"
455
+ },
456
+ "model.language_model.layers.39.self_attn.q_norm": {
457
+ "bits": 16,
458
+ "data_type": "float"
459
+ },
460
+ "model.language_model.layers.4.input_layernorm": {
461
+ "bits": 16,
462
+ "data_type": "float"
463
+ },
464
+ "model.language_model.layers.4.linear_attn.norm": {
465
+ "bits": 16,
466
+ "data_type": "float"
467
+ },
468
+ "model.language_model.layers.4.post_attention_layernorm": {
469
+ "bits": 16,
470
+ "data_type": "float"
471
+ },
472
+ "model.language_model.layers.40.input_layernorm": {
473
+ "bits": 16,
474
+ "data_type": "float"
475
+ },
476
+ "model.language_model.layers.40.linear_attn.norm": {
477
+ "bits": 16,
478
+ "data_type": "float"
479
+ },
480
+ "model.language_model.layers.40.post_attention_layernorm": {
481
+ "bits": 16,
482
+ "data_type": "float"
483
+ },
484
+ "model.language_model.layers.41.input_layernorm": {
485
+ "bits": 16,
486
+ "data_type": "float"
487
+ },
488
+ "model.language_model.layers.41.linear_attn.norm": {
489
+ "bits": 16,
490
+ "data_type": "float"
491
+ },
492
+ "model.language_model.layers.41.post_attention_layernorm": {
493
+ "bits": 16,
494
+ "data_type": "float"
495
+ },
496
+ "model.language_model.layers.42.input_layernorm": {
497
+ "bits": 16,
498
+ "data_type": "float"
499
+ },
500
+ "model.language_model.layers.42.linear_attn.norm": {
501
+ "bits": 16,
502
+ "data_type": "float"
503
+ },
504
+ "model.language_model.layers.42.post_attention_layernorm": {
505
+ "bits": 16,
506
+ "data_type": "float"
507
+ },
508
+ "model.language_model.layers.43.input_layernorm": {
509
+ "bits": 16,
510
+ "data_type": "float"
511
+ },
512
+ "model.language_model.layers.43.post_attention_layernorm": {
513
+ "bits": 16,
514
+ "data_type": "float"
515
+ },
516
+ "model.language_model.layers.43.self_attn.k_norm": {
517
+ "bits": 16,
518
+ "data_type": "float"
519
+ },
520
+ "model.language_model.layers.43.self_attn.q_norm": {
521
+ "bits": 16,
522
+ "data_type": "float"
523
+ },
524
+ "model.language_model.layers.44.input_layernorm": {
525
+ "bits": 16,
526
+ "data_type": "float"
527
+ },
528
+ "model.language_model.layers.44.linear_attn.norm": {
529
+ "bits": 16,
530
+ "data_type": "float"
531
+ },
532
+ "model.language_model.layers.44.post_attention_layernorm": {
533
+ "bits": 16,
534
+ "data_type": "float"
535
+ },
536
+ "model.language_model.layers.45.input_layernorm": {
537
+ "bits": 16,
538
+ "data_type": "float"
539
+ },
540
+ "model.language_model.layers.45.linear_attn.norm": {
541
+ "bits": 16,
542
+ "data_type": "float"
543
+ },
544
+ "model.language_model.layers.45.post_attention_layernorm": {
545
+ "bits": 16,
546
+ "data_type": "float"
547
+ },
548
+ "model.language_model.layers.46.input_layernorm": {
549
+ "bits": 16,
550
+ "data_type": "float"
551
+ },
552
+ "model.language_model.layers.46.linear_attn.norm": {
553
+ "bits": 16,
554
+ "data_type": "float"
555
+ },
556
+ "model.language_model.layers.46.post_attention_layernorm": {
557
+ "bits": 16,
558
+ "data_type": "float"
559
+ },
560
+ "model.language_model.layers.47.input_layernorm": {
561
+ "bits": 16,
562
+ "data_type": "float"
563
+ },
564
+ "model.language_model.layers.47.post_attention_layernorm": {
565
+ "bits": 16,
566
+ "data_type": "float"
567
+ },
568
+ "model.language_model.layers.47.self_attn.k_norm": {
569
+ "bits": 16,
570
+ "data_type": "float"
571
+ },
572
+ "model.language_model.layers.47.self_attn.q_norm": {
573
+ "bits": 16,
574
+ "data_type": "float"
575
+ },
576
+ "model.language_model.layers.48.input_layernorm": {
577
+ "bits": 16,
578
+ "data_type": "float"
579
+ },
580
+ "model.language_model.layers.48.linear_attn.norm": {
581
+ "bits": 16,
582
+ "data_type": "float"
583
+ },
584
+ "model.language_model.layers.48.post_attention_layernorm": {
585
+ "bits": 16,
586
+ "data_type": "float"
587
+ },
588
+ "model.language_model.layers.49.input_layernorm": {
589
+ "bits": 16,
590
+ "data_type": "float"
591
+ },
592
+ "model.language_model.layers.49.linear_attn.norm": {
593
+ "bits": 16,
594
+ "data_type": "float"
595
+ },
596
+ "model.language_model.layers.49.post_attention_layernorm": {
597
+ "bits": 16,
598
+ "data_type": "float"
599
+ },
600
+ "model.language_model.layers.5.input_layernorm": {
601
+ "bits": 16,
602
+ "data_type": "float"
603
+ },
604
+ "model.language_model.layers.5.linear_attn.norm": {
605
+ "bits": 16,
606
+ "data_type": "float"
607
+ },
608
+ "model.language_model.layers.5.post_attention_layernorm": {
609
+ "bits": 16,
610
+ "data_type": "float"
611
+ },
612
+ "model.language_model.layers.50.input_layernorm": {
613
+ "bits": 16,
614
+ "data_type": "float"
615
+ },
616
+ "model.language_model.layers.50.linear_attn.norm": {
617
+ "bits": 16,
618
+ "data_type": "float"
619
+ },
620
+ "model.language_model.layers.50.post_attention_layernorm": {
621
+ "bits": 16,
622
+ "data_type": "float"
623
+ },
624
+ "model.language_model.layers.51.input_layernorm": {
625
+ "bits": 16,
626
+ "data_type": "float"
627
+ },
628
+ "model.language_model.layers.51.post_attention_layernorm": {
629
+ "bits": 16,
630
+ "data_type": "float"
631
+ },
632
+ "model.language_model.layers.51.self_attn.k_norm": {
633
+ "bits": 16,
634
+ "data_type": "float"
635
+ },
636
+ "model.language_model.layers.51.self_attn.q_norm": {
637
+ "bits": 16,
638
+ "data_type": "float"
639
+ },
640
+ "model.language_model.layers.52.input_layernorm": {
641
+ "bits": 16,
642
+ "data_type": "float"
643
+ },
644
+ "model.language_model.layers.52.linear_attn.norm": {
645
+ "bits": 16,
646
+ "data_type": "float"
647
+ },
648
+ "model.language_model.layers.52.post_attention_layernorm": {
649
+ "bits": 16,
650
+ "data_type": "float"
651
+ },
652
+ "model.language_model.layers.53.input_layernorm": {
653
+ "bits": 16,
654
+ "data_type": "float"
655
+ },
656
+ "model.language_model.layers.53.linear_attn.norm": {
657
+ "bits": 16,
658
+ "data_type": "float"
659
+ },
660
+ "model.language_model.layers.53.post_attention_layernorm": {
661
+ "bits": 16,
662
+ "data_type": "float"
663
+ },
664
+ "model.language_model.layers.54.input_layernorm": {
665
+ "bits": 16,
666
+ "data_type": "float"
667
+ },
668
+ "model.language_model.layers.54.linear_attn.norm": {
669
+ "bits": 16,
670
+ "data_type": "float"
671
+ },
672
+ "model.language_model.layers.54.post_attention_layernorm": {
673
+ "bits": 16,
674
+ "data_type": "float"
675
+ },
676
+ "model.language_model.layers.55.input_layernorm": {
677
+ "bits": 16,
678
+ "data_type": "float"
679
+ },
680
+ "model.language_model.layers.55.post_attention_layernorm": {
681
+ "bits": 16,
682
+ "data_type": "float"
683
+ },
684
+ "model.language_model.layers.55.self_attn.k_norm": {
685
+ "bits": 16,
686
+ "data_type": "float"
687
+ },
688
+ "model.language_model.layers.55.self_attn.q_norm": {
689
+ "bits": 16,
690
+ "data_type": "float"
691
+ },
692
+ "model.language_model.layers.56.input_layernorm": {
693
+ "bits": 16,
694
+ "data_type": "float"
695
+ },
696
+ "model.language_model.layers.56.linear_attn.norm": {
697
+ "bits": 16,
698
+ "data_type": "float"
699
+ },
700
+ "model.language_model.layers.56.post_attention_layernorm": {
701
+ "bits": 16,
702
+ "data_type": "float"
703
+ },
704
+ "model.language_model.layers.57.input_layernorm": {
705
+ "bits": 16,
706
+ "data_type": "float"
707
+ },
708
+ "model.language_model.layers.57.linear_attn.norm": {
709
+ "bits": 16,
710
+ "data_type": "float"
711
+ },
712
+ "model.language_model.layers.57.post_attention_layernorm": {
713
+ "bits": 16,
714
+ "data_type": "float"
715
+ },
716
+ "model.language_model.layers.58.input_layernorm": {
717
+ "bits": 16,
718
+ "data_type": "float"
719
+ },
720
+ "model.language_model.layers.58.linear_attn.norm": {
721
+ "bits": 16,
722
+ "data_type": "float"
723
+ },
724
+ "model.language_model.layers.58.post_attention_layernorm": {
725
+ "bits": 16,
726
+ "data_type": "float"
727
+ },
728
+ "model.language_model.layers.59.input_layernorm": {
729
+ "bits": 16,
730
+ "data_type": "float"
731
+ },
732
+ "model.language_model.layers.59.post_attention_layernorm": {
733
+ "bits": 16,
734
+ "data_type": "float"
735
+ },
736
+ "model.language_model.layers.59.self_attn.k_norm": {
737
+ "bits": 16,
738
+ "data_type": "float"
739
+ },
740
+ "model.language_model.layers.59.self_attn.q_norm": {
741
+ "bits": 16,
742
+ "data_type": "float"
743
+ },
744
+ "model.language_model.layers.6.input_layernorm": {
745
+ "bits": 16,
746
+ "data_type": "float"
747
+ },
748
+ "model.language_model.layers.6.linear_attn.norm": {
749
+ "bits": 16,
750
+ "data_type": "float"
751
+ },
752
+ "model.language_model.layers.6.post_attention_layernorm": {
753
+ "bits": 16,
754
+ "data_type": "float"
755
+ },
756
+ "model.language_model.layers.60.input_layernorm": {
757
+ "bits": 16,
758
+ "data_type": "float"
759
+ },
760
+ "model.language_model.layers.60.linear_attn.norm": {
761
+ "bits": 16,
762
+ "data_type": "float"
763
+ },
764
+ "model.language_model.layers.60.post_attention_layernorm": {
765
+ "bits": 16,
766
+ "data_type": "float"
767
+ },
768
+ "model.language_model.layers.61.input_layernorm": {
769
+ "bits": 16,
770
+ "data_type": "float"
771
+ },
772
+ "model.language_model.layers.61.linear_attn.norm": {
773
+ "bits": 16,
774
+ "data_type": "float"
775
+ },
776
+ "model.language_model.layers.61.post_attention_layernorm": {
777
+ "bits": 16,
778
+ "data_type": "float"
779
+ },
780
+ "model.language_model.layers.62.input_layernorm": {
781
+ "bits": 16,
782
+ "data_type": "float"
783
+ },
784
+ "model.language_model.layers.62.linear_attn.norm": {
785
+ "bits": 16,
786
+ "data_type": "float"
787
+ },
788
+ "model.language_model.layers.62.post_attention_layernorm": {
789
+ "bits": 16,
790
+ "data_type": "float"
791
+ },
792
+ "model.language_model.layers.63.input_layernorm": {
793
+ "bits": 16,
794
+ "data_type": "float"
795
+ },
796
+ "model.language_model.layers.63.post_attention_layernorm": {
797
+ "bits": 16,
798
+ "data_type": "float"
799
+ },
800
+ "model.language_model.layers.63.self_attn.k_norm": {
801
+ "bits": 16,
802
+ "data_type": "float"
803
+ },
804
+ "model.language_model.layers.63.self_attn.q_norm": {
805
+ "bits": 16,
806
+ "data_type": "float"
807
+ },
808
+ "model.language_model.layers.7.input_layernorm": {
809
+ "bits": 16,
810
+ "data_type": "float"
811
+ },
812
+ "model.language_model.layers.7.post_attention_layernorm": {
813
+ "bits": 16,
814
+ "data_type": "float"
815
+ },
816
+ "model.language_model.layers.7.self_attn.k_norm": {
817
+ "bits": 16,
818
+ "data_type": "float"
819
+ },
820
+ "model.language_model.layers.7.self_attn.q_norm": {
821
+ "bits": 16,
822
+ "data_type": "float"
823
+ },
824
+ "model.language_model.layers.8.input_layernorm": {
825
+ "bits": 16,
826
+ "data_type": "float"
827
+ },
828
+ "model.language_model.layers.8.linear_attn.norm": {
829
+ "bits": 16,
830
+ "data_type": "float"
831
+ },
832
+ "model.language_model.layers.8.post_attention_layernorm": {
833
+ "bits": 16,
834
+ "data_type": "float"
835
+ },
836
+ "model.language_model.layers.9.input_layernorm": {
837
+ "bits": 16,
838
+ "data_type": "float"
839
+ },
840
+ "model.language_model.layers.9.linear_attn.norm": {
841
+ "bits": 16,
842
+ "data_type": "float"
843
+ },
844
+ "model.language_model.layers.9.post_attention_layernorm": {
845
+ "bits": 16,
846
+ "data_type": "float"
847
+ },
848
+ "model.language_model.norm": {
849
+ "bits": 16,
850
+ "data_type": "float"
851
+ },
852
+ "model.visual.blocks.0.attn.proj": {
853
+ "bits": 16,
854
+ "data_type": "float"
855
+ },
856
+ "model.visual.blocks.0.attn.qkv": {
857
+ "bits": 16,
858
+ "data_type": "float"
859
+ },
860
+ "model.visual.blocks.0.mlp.linear_fc1": {
861
+ "bits": 16,
862
+ "data_type": "float"
863
+ },
864
+ "model.visual.blocks.0.mlp.linear_fc2": {
865
+ "bits": 16,
866
+ "data_type": "float"
867
+ },
868
+ "model.visual.blocks.0.norm1": {
869
+ "bits": 16,
870
+ "data_type": "float"
871
+ },
872
+ "model.visual.blocks.0.norm2": {
873
+ "bits": 16,
874
+ "data_type": "float"
875
+ },
876
+ "model.visual.blocks.1.attn.proj": {
877
+ "bits": 16,
878
+ "data_type": "float"
879
+ },
880
+ "model.visual.blocks.1.attn.qkv": {
881
+ "bits": 16,
882
+ "data_type": "float"
883
+ },
884
+ "model.visual.blocks.1.mlp.linear_fc1": {
885
+ "bits": 16,
886
+ "data_type": "float"
887
+ },
888
+ "model.visual.blocks.1.mlp.linear_fc2": {
889
+ "bits": 16,
890
+ "data_type": "float"
891
+ },
892
+ "model.visual.blocks.1.norm1": {
893
+ "bits": 16,
894
+ "data_type": "float"
895
+ },
896
+ "model.visual.blocks.1.norm2": {
897
+ "bits": 16,
898
+ "data_type": "float"
899
+ },
900
+ "model.visual.blocks.10.attn.proj": {
901
+ "bits": 16,
902
+ "data_type": "float"
903
+ },
904
+ "model.visual.blocks.10.attn.qkv": {
905
+ "bits": 16,
906
+ "data_type": "float"
907
+ },
908
+ "model.visual.blocks.10.mlp.linear_fc1": {
909
+ "bits": 16,
910
+ "data_type": "float"
911
+ },
912
+ "model.visual.blocks.10.mlp.linear_fc2": {
913
+ "bits": 16,
914
+ "data_type": "float"
915
+ },
916
+ "model.visual.blocks.10.norm1": {
917
+ "bits": 16,
918
+ "data_type": "float"
919
+ },
920
+ "model.visual.blocks.10.norm2": {
921
+ "bits": 16,
922
+ "data_type": "float"
923
+ },
924
+ "model.visual.blocks.11.attn.proj": {
925
+ "bits": 16,
926
+ "data_type": "float"
927
+ },
928
+ "model.visual.blocks.11.attn.qkv": {
929
+ "bits": 16,
930
+ "data_type": "float"
931
+ },
932
+ "model.visual.blocks.11.mlp.linear_fc1": {
933
+ "bits": 16,
934
+ "data_type": "float"
935
+ },
936
+ "model.visual.blocks.11.mlp.linear_fc2": {
937
+ "bits": 16,
938
+ "data_type": "float"
939
+ },
940
+ "model.visual.blocks.11.norm1": {
941
+ "bits": 16,
942
+ "data_type": "float"
943
+ },
944
+ "model.visual.blocks.11.norm2": {
945
+ "bits": 16,
946
+ "data_type": "float"
947
+ },
948
+ "model.visual.blocks.12.attn.proj": {
949
+ "bits": 16,
950
+ "data_type": "float"
951
+ },
952
+ "model.visual.blocks.12.attn.qkv": {
953
+ "bits": 16,
954
+ "data_type": "float"
955
+ },
956
+ "model.visual.blocks.12.mlp.linear_fc1": {
957
+ "bits": 16,
958
+ "data_type": "float"
959
+ },
960
+ "model.visual.blocks.12.mlp.linear_fc2": {
961
+ "bits": 16,
962
+ "data_type": "float"
963
+ },
964
+ "model.visual.blocks.12.norm1": {
965
+ "bits": 16,
966
+ "data_type": "float"
967
+ },
968
+ "model.visual.blocks.12.norm2": {
969
+ "bits": 16,
970
+ "data_type": "float"
971
+ },
972
+ "model.visual.blocks.13.attn.proj": {
973
+ "bits": 16,
974
+ "data_type": "float"
975
+ },
976
+ "model.visual.blocks.13.attn.qkv": {
977
+ "bits": 16,
978
+ "data_type": "float"
979
+ },
980
+ "model.visual.blocks.13.mlp.linear_fc1": {
981
+ "bits": 16,
982
+ "data_type": "float"
983
+ },
984
+ "model.visual.blocks.13.mlp.linear_fc2": {
985
+ "bits": 16,
986
+ "data_type": "float"
987
+ },
988
+ "model.visual.blocks.13.norm1": {
989
+ "bits": 16,
990
+ "data_type": "float"
991
+ },
992
+ "model.visual.blocks.13.norm2": {
993
+ "bits": 16,
994
+ "data_type": "float"
995
+ },
996
+ "model.visual.blocks.14.attn.proj": {
997
+ "bits": 16,
998
+ "data_type": "float"
999
+ },
1000
+ "model.visual.blocks.14.attn.qkv": {
1001
+ "bits": 16,
1002
+ "data_type": "float"
1003
+ },
1004
+ "model.visual.blocks.14.mlp.linear_fc1": {
1005
+ "bits": 16,
1006
+ "data_type": "float"
1007
+ },
1008
+ "model.visual.blocks.14.mlp.linear_fc2": {
1009
+ "bits": 16,
1010
+ "data_type": "float"
1011
+ },
1012
+ "model.visual.blocks.14.norm1": {
1013
+ "bits": 16,
1014
+ "data_type": "float"
1015
+ },
1016
+ "model.visual.blocks.14.norm2": {
1017
+ "bits": 16,
1018
+ "data_type": "float"
1019
+ },
1020
+ "model.visual.blocks.15.attn.proj": {
1021
+ "bits": 16,
1022
+ "data_type": "float"
1023
+ },
1024
+ "model.visual.blocks.15.attn.qkv": {
1025
+ "bits": 16,
1026
+ "data_type": "float"
1027
+ },
1028
+ "model.visual.blocks.15.mlp.linear_fc1": {
1029
+ "bits": 16,
1030
+ "data_type": "float"
1031
+ },
1032
+ "model.visual.blocks.15.mlp.linear_fc2": {
1033
+ "bits": 16,
1034
+ "data_type": "float"
1035
+ },
1036
+ "model.visual.blocks.15.norm1": {
1037
+ "bits": 16,
1038
+ "data_type": "float"
1039
+ },
1040
+ "model.visual.blocks.15.norm2": {
1041
+ "bits": 16,
1042
+ "data_type": "float"
1043
+ },
1044
+ "model.visual.blocks.16.attn.proj": {
1045
+ "bits": 16,
1046
+ "data_type": "float"
1047
+ },
1048
+ "model.visual.blocks.16.attn.qkv": {
1049
+ "bits": 16,
1050
+ "data_type": "float"
1051
+ },
1052
+ "model.visual.blocks.16.mlp.linear_fc1": {
1053
+ "bits": 16,
1054
+ "data_type": "float"
1055
+ },
1056
+ "model.visual.blocks.16.mlp.linear_fc2": {
1057
+ "bits": 16,
1058
+ "data_type": "float"
1059
+ },
1060
+ "model.visual.blocks.16.norm1": {
1061
+ "bits": 16,
1062
+ "data_type": "float"
1063
+ },
1064
+ "model.visual.blocks.16.norm2": {
1065
+ "bits": 16,
1066
+ "data_type": "float"
1067
+ },
1068
+ "model.visual.blocks.17.attn.proj": {
1069
+ "bits": 16,
1070
+ "data_type": "float"
1071
+ },
1072
+ "model.visual.blocks.17.attn.qkv": {
1073
+ "bits": 16,
1074
+ "data_type": "float"
1075
+ },
1076
+ "model.visual.blocks.17.mlp.linear_fc1": {
1077
+ "bits": 16,
1078
+ "data_type": "float"
1079
+ },
1080
+ "model.visual.blocks.17.mlp.linear_fc2": {
1081
+ "bits": 16,
1082
+ "data_type": "float"
1083
+ },
1084
+ "model.visual.blocks.17.norm1": {
1085
+ "bits": 16,
1086
+ "data_type": "float"
1087
+ },
1088
+ "model.visual.blocks.17.norm2": {
1089
+ "bits": 16,
1090
+ "data_type": "float"
1091
+ },
1092
+ "model.visual.blocks.18.attn.proj": {
1093
+ "bits": 16,
1094
+ "data_type": "float"
1095
+ },
1096
+ "model.visual.blocks.18.attn.qkv": {
1097
+ "bits": 16,
1098
+ "data_type": "float"
1099
+ },
1100
+ "model.visual.blocks.18.mlp.linear_fc1": {
1101
+ "bits": 16,
1102
+ "data_type": "float"
1103
+ },
1104
+ "model.visual.blocks.18.mlp.linear_fc2": {
1105
+ "bits": 16,
1106
+ "data_type": "float"
1107
+ },
1108
+ "model.visual.blocks.18.norm1": {
1109
+ "bits": 16,
1110
+ "data_type": "float"
1111
+ },
1112
+ "model.visual.blocks.18.norm2": {
1113
+ "bits": 16,
1114
+ "data_type": "float"
1115
+ },
1116
+ "model.visual.blocks.19.attn.proj": {
1117
+ "bits": 16,
1118
+ "data_type": "float"
1119
+ },
1120
+ "model.visual.blocks.19.attn.qkv": {
1121
+ "bits": 16,
1122
+ "data_type": "float"
1123
+ },
1124
+ "model.visual.blocks.19.mlp.linear_fc1": {
1125
+ "bits": 16,
1126
+ "data_type": "float"
1127
+ },
1128
+ "model.visual.blocks.19.mlp.linear_fc2": {
1129
+ "bits": 16,
1130
+ "data_type": "float"
1131
+ },
1132
+ "model.visual.blocks.19.norm1": {
1133
+ "bits": 16,
1134
+ "data_type": "float"
1135
+ },
1136
+ "model.visual.blocks.19.norm2": {
1137
+ "bits": 16,
1138
+ "data_type": "float"
1139
+ },
1140
+ "model.visual.blocks.2.attn.proj": {
1141
+ "bits": 16,
1142
+ "data_type": "float"
1143
+ },
1144
+ "model.visual.blocks.2.attn.qkv": {
1145
+ "bits": 16,
1146
+ "data_type": "float"
1147
+ },
1148
+ "model.visual.blocks.2.mlp.linear_fc1": {
1149
+ "bits": 16,
1150
+ "data_type": "float"
1151
+ },
1152
+ "model.visual.blocks.2.mlp.linear_fc2": {
1153
+ "bits": 16,
1154
+ "data_type": "float"
1155
+ },
1156
+ "model.visual.blocks.2.norm1": {
1157
+ "bits": 16,
1158
+ "data_type": "float"
1159
+ },
1160
+ "model.visual.blocks.2.norm2": {
1161
+ "bits": 16,
1162
+ "data_type": "float"
1163
+ },
1164
+ "model.visual.blocks.20.attn.proj": {
1165
+ "bits": 16,
1166
+ "data_type": "float"
1167
+ },
1168
+ "model.visual.blocks.20.attn.qkv": {
1169
+ "bits": 16,
1170
+ "data_type": "float"
1171
+ },
1172
+ "model.visual.blocks.20.mlp.linear_fc1": {
1173
+ "bits": 16,
1174
+ "data_type": "float"
1175
+ },
1176
+ "model.visual.blocks.20.mlp.linear_fc2": {
1177
+ "bits": 16,
1178
+ "data_type": "float"
1179
+ },
1180
+ "model.visual.blocks.20.norm1": {
1181
+ "bits": 16,
1182
+ "data_type": "float"
1183
+ },
1184
+ "model.visual.blocks.20.norm2": {
1185
+ "bits": 16,
1186
+ "data_type": "float"
1187
+ },
1188
+ "model.visual.blocks.21.attn.proj": {
1189
+ "bits": 16,
1190
+ "data_type": "float"
1191
+ },
1192
+ "model.visual.blocks.21.attn.qkv": {
1193
+ "bits": 16,
1194
+ "data_type": "float"
1195
+ },
1196
+ "model.visual.blocks.21.mlp.linear_fc1": {
1197
+ "bits": 16,
1198
+ "data_type": "float"
1199
+ },
1200
+ "model.visual.blocks.21.mlp.linear_fc2": {
1201
+ "bits": 16,
1202
+ "data_type": "float"
1203
+ },
1204
+ "model.visual.blocks.21.norm1": {
1205
+ "bits": 16,
1206
+ "data_type": "float"
1207
+ },
1208
+ "model.visual.blocks.21.norm2": {
1209
+ "bits": 16,
1210
+ "data_type": "float"
1211
+ },
1212
+ "model.visual.blocks.22.attn.proj": {
1213
+ "bits": 16,
1214
+ "data_type": "float"
1215
+ },
1216
+ "model.visual.blocks.22.attn.qkv": {
1217
+ "bits": 16,
1218
+ "data_type": "float"
1219
+ },
1220
+ "model.visual.blocks.22.mlp.linear_fc1": {
1221
+ "bits": 16,
1222
+ "data_type": "float"
1223
+ },
1224
+ "model.visual.blocks.22.mlp.linear_fc2": {
1225
+ "bits": 16,
1226
+ "data_type": "float"
1227
+ },
1228
+ "model.visual.blocks.22.norm1": {
1229
+ "bits": 16,
1230
+ "data_type": "float"
1231
+ },
1232
+ "model.visual.blocks.22.norm2": {
1233
+ "bits": 16,
1234
+ "data_type": "float"
1235
+ },
1236
+ "model.visual.blocks.23.attn.proj": {
1237
+ "bits": 16,
1238
+ "data_type": "float"
1239
+ },
1240
+ "model.visual.blocks.23.attn.qkv": {
1241
+ "bits": 16,
1242
+ "data_type": "float"
1243
+ },
1244
+ "model.visual.blocks.23.mlp.linear_fc1": {
1245
+ "bits": 16,
1246
+ "data_type": "float"
1247
+ },
1248
+ "model.visual.blocks.23.mlp.linear_fc2": {
1249
+ "bits": 16,
1250
+ "data_type": "float"
1251
+ },
1252
+ "model.visual.blocks.23.norm1": {
1253
+ "bits": 16,
1254
+ "data_type": "float"
1255
+ },
1256
+ "model.visual.blocks.23.norm2": {
1257
+ "bits": 16,
1258
+ "data_type": "float"
1259
+ },
1260
+ "model.visual.blocks.24.attn.proj": {
1261
+ "bits": 16,
1262
+ "data_type": "float"
1263
+ },
1264
+ "model.visual.blocks.24.attn.qkv": {
1265
+ "bits": 16,
1266
+ "data_type": "float"
1267
+ },
1268
+ "model.visual.blocks.24.mlp.linear_fc1": {
1269
+ "bits": 16,
1270
+ "data_type": "float"
1271
+ },
1272
+ "model.visual.blocks.24.mlp.linear_fc2": {
1273
+ "bits": 16,
1274
+ "data_type": "float"
1275
+ },
1276
+ "model.visual.blocks.24.norm1": {
1277
+ "bits": 16,
1278
+ "data_type": "float"
1279
+ },
1280
+ "model.visual.blocks.24.norm2": {
1281
+ "bits": 16,
1282
+ "data_type": "float"
1283
+ },
1284
+ "model.visual.blocks.25.attn.proj": {
1285
+ "bits": 16,
1286
+ "data_type": "float"
1287
+ },
1288
+ "model.visual.blocks.25.attn.qkv": {
1289
+ "bits": 16,
1290
+ "data_type": "float"
1291
+ },
1292
+ "model.visual.blocks.25.mlp.linear_fc1": {
1293
+ "bits": 16,
1294
+ "data_type": "float"
1295
+ },
1296
+ "model.visual.blocks.25.mlp.linear_fc2": {
1297
+ "bits": 16,
1298
+ "data_type": "float"
1299
+ },
1300
+ "model.visual.blocks.25.norm1": {
1301
+ "bits": 16,
1302
+ "data_type": "float"
1303
+ },
1304
+ "model.visual.blocks.25.norm2": {
1305
+ "bits": 16,
1306
+ "data_type": "float"
1307
+ },
1308
+ "model.visual.blocks.26.attn.proj": {
1309
+ "bits": 16,
1310
+ "data_type": "float"
1311
+ },
1312
+ "model.visual.blocks.26.attn.qkv": {
1313
+ "bits": 16,
1314
+ "data_type": "float"
1315
+ },
1316
+ "model.visual.blocks.26.mlp.linear_fc1": {
1317
+ "bits": 16,
1318
+ "data_type": "float"
1319
+ },
1320
+ "model.visual.blocks.26.mlp.linear_fc2": {
1321
+ "bits": 16,
1322
+ "data_type": "float"
1323
+ },
1324
+ "model.visual.blocks.26.norm1": {
1325
+ "bits": 16,
1326
+ "data_type": "float"
1327
+ },
1328
+ "model.visual.blocks.26.norm2": {
1329
+ "bits": 16,
1330
+ "data_type": "float"
1331
+ },
1332
+ "model.visual.blocks.3.attn.proj": {
1333
+ "bits": 16,
1334
+ "data_type": "float"
1335
+ },
1336
+ "model.visual.blocks.3.attn.qkv": {
1337
+ "bits": 16,
1338
+ "data_type": "float"
1339
+ },
1340
+ "model.visual.blocks.3.mlp.linear_fc1": {
1341
+ "bits": 16,
1342
+ "data_type": "float"
1343
+ },
1344
+ "model.visual.blocks.3.mlp.linear_fc2": {
1345
+ "bits": 16,
1346
+ "data_type": "float"
1347
+ },
1348
+ "model.visual.blocks.3.norm1": {
1349
+ "bits": 16,
1350
+ "data_type": "float"
1351
+ },
1352
+ "model.visual.blocks.3.norm2": {
1353
+ "bits": 16,
1354
+ "data_type": "float"
1355
+ },
1356
+ "model.visual.blocks.4.attn.proj": {
1357
+ "bits": 16,
1358
+ "data_type": "float"
1359
+ },
1360
+ "model.visual.blocks.4.attn.qkv": {
1361
+ "bits": 16,
1362
+ "data_type": "float"
1363
+ },
1364
+ "model.visual.blocks.4.mlp.linear_fc1": {
1365
+ "bits": 16,
1366
+ "data_type": "float"
1367
+ },
1368
+ "model.visual.blocks.4.mlp.linear_fc2": {
1369
+ "bits": 16,
1370
+ "data_type": "float"
1371
+ },
1372
+ "model.visual.blocks.4.norm1": {
1373
+ "bits": 16,
1374
+ "data_type": "float"
1375
+ },
1376
+ "model.visual.blocks.4.norm2": {
1377
+ "bits": 16,
1378
+ "data_type": "float"
1379
+ },
1380
+ "model.visual.blocks.5.attn.proj": {
1381
+ "bits": 16,
1382
+ "data_type": "float"
1383
+ },
1384
+ "model.visual.blocks.5.attn.qkv": {
1385
+ "bits": 16,
1386
+ "data_type": "float"
1387
+ },
1388
+ "model.visual.blocks.5.mlp.linear_fc1": {
1389
+ "bits": 16,
1390
+ "data_type": "float"
1391
+ },
1392
+ "model.visual.blocks.5.mlp.linear_fc2": {
1393
+ "bits": 16,
1394
+ "data_type": "float"
1395
+ },
1396
+ "model.visual.blocks.5.norm1": {
1397
+ "bits": 16,
1398
+ "data_type": "float"
1399
+ },
1400
+ "model.visual.blocks.5.norm2": {
1401
+ "bits": 16,
1402
+ "data_type": "float"
1403
+ },
1404
+ "model.visual.blocks.6.attn.proj": {
1405
+ "bits": 16,
1406
+ "data_type": "float"
1407
+ },
1408
+ "model.visual.blocks.6.attn.qkv": {
1409
+ "bits": 16,
1410
+ "data_type": "float"
1411
+ },
1412
+ "model.visual.blocks.6.mlp.linear_fc1": {
1413
+ "bits": 16,
1414
+ "data_type": "float"
1415
+ },
1416
+ "model.visual.blocks.6.mlp.linear_fc2": {
1417
+ "bits": 16,
1418
+ "data_type": "float"
1419
+ },
1420
+ "model.visual.blocks.6.norm1": {
1421
+ "bits": 16,
1422
+ "data_type": "float"
1423
+ },
1424
+ "model.visual.blocks.6.norm2": {
1425
+ "bits": 16,
1426
+ "data_type": "float"
1427
+ },
1428
+ "model.visual.blocks.7.attn.proj": {
1429
+ "bits": 16,
1430
+ "data_type": "float"
1431
+ },
1432
+ "model.visual.blocks.7.attn.qkv": {
1433
+ "bits": 16,
1434
+ "data_type": "float"
1435
+ },
1436
+ "model.visual.blocks.7.mlp.linear_fc1": {
1437
+ "bits": 16,
1438
+ "data_type": "float"
1439
+ },
1440
+ "model.visual.blocks.7.mlp.linear_fc2": {
1441
+ "bits": 16,
1442
+ "data_type": "float"
1443
+ },
1444
+ "model.visual.blocks.7.norm1": {
1445
+ "bits": 16,
1446
+ "data_type": "float"
1447
+ },
1448
+ "model.visual.blocks.7.norm2": {
1449
+ "bits": 16,
1450
+ "data_type": "float"
1451
+ },
1452
+ "model.visual.blocks.8.attn.proj": {
1453
+ "bits": 16,
1454
+ "data_type": "float"
1455
+ },
1456
+ "model.visual.blocks.8.attn.qkv": {
1457
+ "bits": 16,
1458
+ "data_type": "float"
1459
+ },
1460
+ "model.visual.blocks.8.mlp.linear_fc1": {
1461
+ "bits": 16,
1462
+ "data_type": "float"
1463
+ },
1464
+ "model.visual.blocks.8.mlp.linear_fc2": {
1465
+ "bits": 16,
1466
+ "data_type": "float"
1467
+ },
1468
+ "model.visual.blocks.8.norm1": {
1469
+ "bits": 16,
1470
+ "data_type": "float"
1471
+ },
1472
+ "model.visual.blocks.8.norm2": {
1473
+ "bits": 16,
1474
+ "data_type": "float"
1475
+ },
1476
+ "model.visual.blocks.9.attn.proj": {
1477
+ "bits": 16,
1478
+ "data_type": "float"
1479
+ },
1480
+ "model.visual.blocks.9.attn.qkv": {
1481
+ "bits": 16,
1482
+ "data_type": "float"
1483
+ },
1484
+ "model.visual.blocks.9.mlp.linear_fc1": {
1485
+ "bits": 16,
1486
+ "data_type": "float"
1487
+ },
1488
+ "model.visual.blocks.9.mlp.linear_fc2": {
1489
+ "bits": 16,
1490
+ "data_type": "float"
1491
+ },
1492
+ "model.visual.blocks.9.norm1": {
1493
+ "bits": 16,
1494
+ "data_type": "float"
1495
+ },
1496
+ "model.visual.blocks.9.norm2": {
1497
+ "bits": 16,
1498
+ "data_type": "float"
1499
+ },
1500
+ "model.visual.merger.linear_fc1": {
1501
+ "bits": 16,
1502
+ "data_type": "float"
1503
+ },
1504
+ "model.visual.merger.linear_fc2": {
1505
+ "bits": 16,
1506
+ "data_type": "float"
1507
+ },
1508
+ "model.visual.merger.norm": {
1509
+ "bits": 16,
1510
+ "data_type": "float"
1511
+ },
1512
+ "mtp.layers.0.input_layernorm": {
1513
+ "bits": 16,
1514
+ "data_type": "float"
1515
+ },
1516
+ "mtp.layers.0.post_attention_layernorm": {
1517
+ "bits": 16,
1518
+ "data_type": "float"
1519
+ },
1520
+ "mtp.layers.0.self_attn.k_norm": {
1521
+ "bits": 16,
1522
+ "data_type": "float"
1523
+ },
1524
+ "mtp.layers.0.self_attn.q_norm": {
1525
+ "bits": 16,
1526
+ "data_type": "float"
1527
+ },
1528
+ "mtp.norm": {
1529
+ "bits": 16,
1530
+ "data_type": "float"
1531
+ },
1532
+ "mtp.pre_fc_norm_hidden": {
1533
+ "bits": 16,
1534
+ "data_type": "float"
1535
+ }
1536
+ }
1537
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f32ce20dc35f57a7f9ad1eac03525bd7d30f9df8cea6507e958279cc3657706
3
+ size 19989492
tokenizer_config.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "max_length": null,
15
+ "model_max_length": 262144,
16
+ "model_specific_special_tokens": {
17
+ "audio_bos_token": "<|audio_start|>",
18
+ "audio_eos_token": "<|audio_end|>",
19
+ "audio_token": "<|audio_pad|>",
20
+ "image_token": "<|image_pad|>",
21
+ "video_token": "<|video_pad|>",
22
+ "vision_bos_token": "<|vision_start|>",
23
+ "vision_eos_token": "<|vision_end|>"
24
+ },
25
+ "pad_to_multiple_of": null,
26
+ "pad_token": "<|endoftext|>",
27
+ "pad_token_type_id": 0,
28
+ "padding_side": "left",
29
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "split_special_tokens": false,
32
+ "tokenizer_class": "Qwen2Tokenizer",
33
+ "unk_token": null,
34
+ "video_token": "<|video_pad|>",
35
+ "vision_bos_token": "<|vision_start|>",
36
+ "vision_eos_token": "<|vision_end|>",
37
+ "added_tokens_decoder": {
38
+ "248044": {
39
+ "content": "<|endoftext|>",
40
+ "single_word": false,
41
+ "lstrip": false,
42
+ "rstrip": false,
43
+ "normalized": false,
44
+ "special": true
45
+ },
46
+ "248045": {
47
+ "content": "<|im_start|>",
48
+ "single_word": false,
49
+ "lstrip": false,
50
+ "rstrip": false,
51
+ "normalized": false,
52
+ "special": true
53
+ },
54
+ "248046": {
55
+ "content": "<|im_end|>",
56
+ "single_word": false,
57
+ "lstrip": false,
58
+ "rstrip": false,
59
+ "normalized": false,
60
+ "special": true
61
+ },
62
+ "248047": {
63
+ "content": "<|object_ref_start|>",
64
+ "single_word": false,
65
+ "lstrip": false,
66
+ "rstrip": false,
67
+ "normalized": false,
68
+ "special": true
69
+ },
70
+ "248048": {
71
+ "content": "<|object_ref_end|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ "248049": {
79
+ "content": "<|box_start|>",
80
+ "single_word": false,
81
+ "lstrip": false,
82
+ "rstrip": false,
83
+ "normalized": false,
84
+ "special": true
85
+ },
86
+ "248050": {
87
+ "content": "<|box_end|>",
88
+ "single_word": false,
89
+ "lstrip": false,
90
+ "rstrip": false,
91
+ "normalized": false,
92
+ "special": true
93
+ },
94
+ "248051": {
95
+ "content": "<|quad_start|>",
96
+ "single_word": false,
97
+ "lstrip": false,
98
+ "rstrip": false,
99
+ "normalized": false,
100
+ "special": true
101
+ },
102
+ "248052": {
103
+ "content": "<|quad_end|>",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": false,
108
+ "special": true
109
+ },
110
+ "248053": {
111
+ "content": "<|vision_start|>",
112
+ "single_word": false,
113
+ "lstrip": false,
114
+ "rstrip": false,
115
+ "normalized": false,
116
+ "special": true
117
+ },
118
+ "248054": {
119
+ "content": "<|vision_end|>",
120
+ "single_word": false,
121
+ "lstrip": false,
122
+ "rstrip": false,
123
+ "normalized": false,
124
+ "special": true
125
+ },
126
+ "248055": {
127
+ "content": "<|vision_pad|>",
128
+ "single_word": false,
129
+ "lstrip": false,
130
+ "rstrip": false,
131
+ "normalized": false,
132
+ "special": true
133
+ },
134
+ "248056": {
135
+ "content": "<|image_pad|>",
136
+ "single_word": false,
137
+ "lstrip": false,
138
+ "rstrip": false,
139
+ "normalized": false,
140
+ "special": true
141
+ },
142
+ "248057": {
143
+ "content": "<|video_pad|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ "248058": {
151
+ "content": "<tool_call>",
152
+ "single_word": false,
153
+ "lstrip": false,
154
+ "rstrip": false,
155
+ "normalized": false,
156
+ "special": false
157
+ },
158
+ "248059": {
159
+ "content": "</tool_call>",
160
+ "single_word": false,
161
+ "lstrip": false,
162
+ "rstrip": false,
163
+ "normalized": false,
164
+ "special": false
165
+ },
166
+ "248060": {
167
+ "content": "<|fim_prefix|>",
168
+ "single_word": false,
169
+ "lstrip": false,
170
+ "rstrip": false,
171
+ "normalized": false,
172
+ "special": false
173
+ },
174
+ "248061": {
175
+ "content": "<|fim_middle|>",
176
+ "single_word": false,
177
+ "lstrip": false,
178
+ "rstrip": false,
179
+ "normalized": false,
180
+ "special": false
181
+ },
182
+ "248062": {
183
+ "content": "<|fim_suffix|>",
184
+ "single_word": false,
185
+ "lstrip": false,
186
+ "rstrip": false,
187
+ "normalized": false,
188
+ "special": false
189
+ },
190
+ "248063": {
191
+ "content": "<|fim_pad|>",
192
+ "single_word": false,
193
+ "lstrip": false,
194
+ "rstrip": false,
195
+ "normalized": false,
196
+ "special": false
197
+ },
198
+ "248064": {
199
+ "content": "<|repo_name|>",
200
+ "single_word": false,
201
+ "lstrip": false,
202
+ "rstrip": false,
203
+ "normalized": false,
204
+ "special": false
205
+ },
206
+ "248065": {
207
+ "content": "<|file_sep|>",
208
+ "single_word": false,
209
+ "lstrip": false,
210
+ "rstrip": false,
211
+ "normalized": false,
212
+ "special": false
213
+ },
214
+ "248066": {
215
+ "content": "<tool_response>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": false
221
+ },
222
+ "248067": {
223
+ "content": "</tool_response>",
224
+ "single_word": false,
225
+ "lstrip": false,
226
+ "rstrip": false,
227
+ "normalized": false,
228
+ "special": false
229
+ },
230
+ "248068": {
231
+ "content": "<think>",
232
+ "single_word": false,
233
+ "lstrip": false,
234
+ "rstrip": false,
235
+ "normalized": false,
236
+ "special": false
237
+ },
238
+ "248069": {
239
+ "content": "</think>",
240
+ "single_word": false,
241
+ "lstrip": false,
242
+ "rstrip": false,
243
+ "normalized": false,
244
+ "special": false
245
+ },
246
+ "248070": {
247
+ "content": "<|audio_start|>",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": false,
252
+ "special": true
253
+ },
254
+ "248071": {
255
+ "content": "<|audio_end|>",
256
+ "single_word": false,
257
+ "lstrip": false,
258
+ "rstrip": false,
259
+ "normalized": false,
260
+ "special": true
261
+ },
262
+ "248072": {
263
+ "content": "<tts_pad>",
264
+ "single_word": false,
265
+ "lstrip": false,
266
+ "rstrip": false,
267
+ "normalized": false,
268
+ "special": true
269
+ },
270
+ "248073": {
271
+ "content": "<tts_text_bos>",
272
+ "single_word": false,
273
+ "lstrip": false,
274
+ "rstrip": false,
275
+ "normalized": false,
276
+ "special": true
277
+ },
278
+ "248074": {
279
+ "content": "<tts_text_eod>",
280
+ "single_word": false,
281
+ "lstrip": false,
282
+ "rstrip": false,
283
+ "normalized": false,
284
+ "special": true
285
+ },
286
+ "248075": {
287
+ "content": "<tts_text_bos_single>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ "248076": {
295
+ "content": "<|audio_pad|>",
296
+ "single_word": false,
297
+ "lstrip": false,
298
+ "rstrip": false,
299
+ "normalized": false,
300
+ "special": true
301
+ }
302
+ },
303
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}"
304
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff