gyung commited on
Commit
85915cd
·
verified ·
1 Parent(s): 49cee42

Upload reloadable Harness-1 bootstrap LoRA adapter

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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LiquidAI/LFM2.5-8B-A1B
3
+ library_name: peft
4
+ tags:
5
+ - lora
6
+ - terminal
7
+ - tool-use
8
+ - harness-1
9
+ - lfm2
10
+ - lfm2.5
11
+ - sft
12
+ license: other
13
+ ---
14
+
15
+ # LFM2.5-8B-A1B Harness-1 LoRA SFT R32 Reloadable
16
+
17
+ This repository contains a PEFT/LoRA adapter for `LiquidAI/LFM2.5-8B-A1B` trained on a local Harness-1-style terminal/tool-use SFT bootstrap dataset.
18
+
19
+ ## Training Summary
20
+
21
+ - Base model: `LiquidAI/LFM2.5-8B-A1B`
22
+ - Method: LoRA SFT, rank 32, alpha 64, bf16
23
+ - Context length: 32,768
24
+ - Hardware: 8 x NVIDIA H200
25
+ - Effective batch size: 128
26
+ - Epochs: 3
27
+ - Train rows after packing/cache: 493
28
+ - Runtime: 320.3 seconds
29
+ - Final train loss: 4.673
30
+
31
+ ## LoRA Target Modules
32
+
33
+ This adapter intentionally avoids LFM MoE expert `target_parameters` because the current PEFT/Unsloth stack can save those tensors but reload/merge them with mismatched expert dimensions. The reloadable target set is:
34
+
35
+ `q_proj,k_proj,v_proj,out_proj,in_proj,w1,w2,w3,gate`
36
+
37
+ ## Data Note
38
+
39
+ The SFT data was generated from public BrowseComp+ style query/gold-document records into deterministic Harness-style tool trajectories. It is a bootstrap run, not the original paper's GPT-5.4 teacher trajectory set.
40
+
41
+ ## Use
42
+
43
+ Load with PEFT on top of the base model:
44
+
45
+ ```python
46
+ from peft import PeftModel
47
+ from transformers import AutoModelForCausalLM, AutoTokenizer
48
+
49
+ base = "LiquidAI/LFM2.5-8B-A1B"
50
+ adapter = "LLM-OS-Models/LFM2.5-8B-A1B-Harness1-LoRA-SFT-R32-Reloadable"
51
+
52
+ tok = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
53
+ model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", trust_remote_code=True)
54
+ model = PeftModel.from_pretrained(model, adapter)
55
+ ```
adapter_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Lfm2MoeForCausalLM",
7
+ "parent_library": "transformers.models.lfm2_moe.modeling_lfm2_moe",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "LiquidAI/LFM2.5-8B-A1B",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 32,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "in_proj",
39
+ "k_proj",
40
+ "gate",
41
+ "w2",
42
+ "out_proj",
43
+ "q_proj",
44
+ "w3",
45
+ "w1"
46
+ ],
47
+ "target_parameters": null,
48
+ "task_type": "CAUSAL_LM",
49
+ "trainable_token_indices": null,
50
+ "use_bdlora": null,
51
+ "use_dora": false,
52
+ "use_qalora": false,
53
+ "use_rslora": false
54
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a43d219fae21f03710d9b14a46dfe874ae6a776be7b9928467ffd45c7fa260c
3
+ size 51493768
chat_template.jinja ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + arg_value + "'" -}}
7
+ {%- elif arg_value is mapping -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- else -%}
18
+ {%- set _ns = namespace(result="") -%}
19
+ {%- for item in content -%}
20
+ {%- if item["type"] == "image" -%}
21
+ {%- set _ns.result = _ns.result + "<image>" -%}
22
+ {%- elif item["type"] == "text" -%}
23
+ {%- set _ns.result = _ns.result + item["text"] -%}
24
+ {%- else -%}
25
+ {%- set _ns.result = _ns.result + item | tojson -%}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {{- _ns.result -}}
29
+ {%- endif -%}
30
+ {%- endmacro -%}
31
+
32
+ {%- macro render_tool_calls(tool_calls) -%}
33
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
34
+ {%- for tool_call in tool_calls -%}
35
+ {%- set func_name = tool_call["function"]["name"] -%}
36
+ {%- set func_args = tool_call["function"]["arguments"] -%}
37
+ {%- set args_ns = namespace(arg_strings=[]) -%}
38
+ {%- for arg_name, arg_value in func_args.items() -%}
39
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
40
+ {%- endfor -%}
41
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
42
+ {%- endfor -%}
43
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
44
+ {%- endmacro -%}
45
+
46
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
47
+ {%- if messages[0]["role"] == "system" -%}
48
+ {%- if messages[0].get("content") -%}
49
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
50
+ {%- endif -%}
51
+ {%- set messages = messages[1:] -%}
52
+ {%- endif -%}
53
+ {%- if tools -%}
54
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
55
+ {%- for tool in tools -%}
56
+ {%- if tool is not string -%}
57
+ {%- set tool = tool | tojson -%}
58
+ {%- endif -%}
59
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
60
+ {%- if not loop.last -%}
61
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
62
+ {%- endif -%}
63
+ {%- endfor -%}
64
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
65
+ {%- endif -%}
66
+ {%- if ns.system_prompt -%}
67
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
68
+ {%- endif -%}
69
+ {%- for message in messages -%}
70
+ {%- if message["role"] == "user" -%}
71
+ {%- set ns.last_user_index = loop.index0 -%}
72
+ {%- endif -%}
73
+ {%- endfor -%}
74
+ {%- for message in messages -%}
75
+ {{- "<|im_start|>" + message.role + "\n" -}}
76
+ {%- if message.role == "assistant" -%}
77
+ {%- generation -%}
78
+ {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
79
+ {{- "<think>" + message.thinking + "</think>" -}}
80
+ {%- endif -%}
81
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
82
+ {%- set _has_cfm = false -%}
83
+ {%- if message.content is defined -%}
84
+ {%- set content = parse_content(message.content) -%}
85
+ {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
86
+ {%- if "</think>" in content -%}
87
+ {%- set content = content.split("</think>")[-1] | trim -%}
88
+ {%- endif -%}
89
+ {%- endif -%}
90
+ {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
91
+ {%- set _has_cfm = true -%}
92
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
93
+ {{- content[:_trunc_len] -}}
94
+ {%- else -%}
95
+ {{- content -}}
96
+ {%- endif -%}
97
+ {%- endif -%}
98
+ {%- if message.tool_calls is defined -%}
99
+ {{- render_tool_calls(message.tool_calls) -}}
100
+ {%- endif -%}
101
+ {%- if _has_cfm -%}
102
+ {{- _cfm_tag -}}
103
+ {%- endif -%}
104
+ {{- "<|im_end|>\n" -}}
105
+ {%- endgeneration -%}
106
+ {%- else %}
107
+ {%- if message.get("content") -%}
108
+ {{- parse_content(message["content"]) -}}
109
+ {%- endif -%}
110
+ {{- "<|im_end|>\n" -}}
111
+ {%- endif %}
112
+ {%- endfor -%}
113
+ {%- if add_generation_prompt -%}
114
+ {{- "<|im_start|>assistant\n" -}}
115
+ {%- endif -%}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
tokenizer_config.json ADDED
@@ -0,0 +1,1006 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": false,
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<|pad|>",
9
+ "padding_side": "left",
10
+ "tokenizer_class": "TokenizersBackend",
11
+ "use_default_system_prompt": false,
12
+ "added_tokens_decoder": {
13
+ "124893": {
14
+ "content": "<|pad|>",
15
+ "single_word": false,
16
+ "lstrip": false,
17
+ "rstrip": false,
18
+ "normalized": false,
19
+ "special": true
20
+ },
21
+ "124894": {
22
+ "content": "<|startoftext|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ "124895": {
30
+ "content": "<|endoftext|>",
31
+ "single_word": false,
32
+ "lstrip": false,
33
+ "rstrip": false,
34
+ "normalized": false,
35
+ "special": true
36
+ },
37
+ "124896": {
38
+ "content": "<|fim_pre|>",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": false,
43
+ "special": true
44
+ },
45
+ "124897": {
46
+ "content": "<|fim_mid|>",
47
+ "single_word": false,
48
+ "lstrip": false,
49
+ "rstrip": false,
50
+ "normalized": false,
51
+ "special": true
52
+ },
53
+ "124898": {
54
+ "content": "<|fim_suf|>",
55
+ "single_word": false,
56
+ "lstrip": false,
57
+ "rstrip": false,
58
+ "normalized": false,
59
+ "special": true
60
+ },
61
+ "124899": {
62
+ "content": "<|im_start|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ "124900": {
70
+ "content": "<|im_end|>",
71
+ "single_word": false,
72
+ "lstrip": false,
73
+ "rstrip": false,
74
+ "normalized": false,
75
+ "special": true
76
+ },
77
+ "124901": {
78
+ "content": "<think>",
79
+ "single_word": false,
80
+ "lstrip": false,
81
+ "rstrip": false,
82
+ "normalized": false,
83
+ "special": false
84
+ },
85
+ "124902": {
86
+ "content": "</think>",
87
+ "single_word": false,
88
+ "lstrip": false,
89
+ "rstrip": false,
90
+ "normalized": false,
91
+ "special": false
92
+ },
93
+ "124903": {
94
+ "content": "<|tool_list_start|>",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": false,
99
+ "special": true
100
+ },
101
+ "124904": {
102
+ "content": "<|tool_list_end|>",
103
+ "single_word": false,
104
+ "lstrip": false,
105
+ "rstrip": false,
106
+ "normalized": false,
107
+ "special": true
108
+ },
109
+ "124905": {
110
+ "content": "<|tool_call_start|>",
111
+ "single_word": false,
112
+ "lstrip": false,
113
+ "rstrip": false,
114
+ "normalized": false,
115
+ "special": false
116
+ },
117
+ "124906": {
118
+ "content": "<|tool_call_end|>",
119
+ "single_word": false,
120
+ "lstrip": false,
121
+ "rstrip": false,
122
+ "normalized": false,
123
+ "special": false
124
+ },
125
+ "124907": {
126
+ "content": "<image>",
127
+ "single_word": false,
128
+ "lstrip": false,
129
+ "rstrip": false,
130
+ "normalized": false,
131
+ "special": true
132
+ },
133
+ "124908": {
134
+ "content": "<|img_row_1_col_1|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ "124909": {
142
+ "content": "<|img_row_1_col_2|>",
143
+ "single_word": false,
144
+ "lstrip": false,
145
+ "rstrip": false,
146
+ "normalized": false,
147
+ "special": true
148
+ },
149
+ "124910": {
150
+ "content": "<|img_row_1_col_3|>",
151
+ "single_word": false,
152
+ "lstrip": false,
153
+ "rstrip": false,
154
+ "normalized": false,
155
+ "special": true
156
+ },
157
+ "124911": {
158
+ "content": "<|img_row_1_col_4|>",
159
+ "single_word": false,
160
+ "lstrip": false,
161
+ "rstrip": false,
162
+ "normalized": false,
163
+ "special": true
164
+ },
165
+ "124912": {
166
+ "content": "<|img_row_1_col_5|>",
167
+ "single_word": false,
168
+ "lstrip": false,
169
+ "rstrip": false,
170
+ "normalized": false,
171
+ "special": true
172
+ },
173
+ "124913": {
174
+ "content": "<|img_row_1_col_6|>",
175
+ "single_word": false,
176
+ "lstrip": false,
177
+ "rstrip": false,
178
+ "normalized": false,
179
+ "special": true
180
+ },
181
+ "124914": {
182
+ "content": "<|img_row_1_col_7|>",
183
+ "single_word": false,
184
+ "lstrip": false,
185
+ "rstrip": false,
186
+ "normalized": false,
187
+ "special": true
188
+ },
189
+ "124915": {
190
+ "content": "<|img_row_1_col_8|>",
191
+ "single_word": false,
192
+ "lstrip": false,
193
+ "rstrip": false,
194
+ "normalized": false,
195
+ "special": true
196
+ },
197
+ "124916": {
198
+ "content": "<|img_row_1_col_9|>",
199
+ "single_word": false,
200
+ "lstrip": false,
201
+ "rstrip": false,
202
+ "normalized": false,
203
+ "special": true
204
+ },
205
+ "124917": {
206
+ "content": "<|img_row_1_col_10|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ "124918": {
214
+ "content": "<|img_row_2_col_1|>",
215
+ "single_word": false,
216
+ "lstrip": false,
217
+ "rstrip": false,
218
+ "normalized": false,
219
+ "special": true
220
+ },
221
+ "124919": {
222
+ "content": "<|img_row_2_col_2|>",
223
+ "single_word": false,
224
+ "lstrip": false,
225
+ "rstrip": false,
226
+ "normalized": false,
227
+ "special": true
228
+ },
229
+ "124920": {
230
+ "content": "<|img_row_2_col_3|>",
231
+ "single_word": false,
232
+ "lstrip": false,
233
+ "rstrip": false,
234
+ "normalized": false,
235
+ "special": true
236
+ },
237
+ "124921": {
238
+ "content": "<|img_row_2_col_4|>",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": true
244
+ },
245
+ "124922": {
246
+ "content": "<|img_row_2_col_5|>",
247
+ "single_word": false,
248
+ "lstrip": false,
249
+ "rstrip": false,
250
+ "normalized": false,
251
+ "special": true
252
+ },
253
+ "124923": {
254
+ "content": "<|img_row_2_col_6|>",
255
+ "single_word": false,
256
+ "lstrip": false,
257
+ "rstrip": false,
258
+ "normalized": false,
259
+ "special": true
260
+ },
261
+ "124924": {
262
+ "content": "<|img_row_2_col_7|>",
263
+ "single_word": false,
264
+ "lstrip": false,
265
+ "rstrip": false,
266
+ "normalized": false,
267
+ "special": true
268
+ },
269
+ "124925": {
270
+ "content": "<|img_row_2_col_8|>",
271
+ "single_word": false,
272
+ "lstrip": false,
273
+ "rstrip": false,
274
+ "normalized": false,
275
+ "special": true
276
+ },
277
+ "124926": {
278
+ "content": "<|img_row_2_col_9|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ "124927": {
286
+ "content": "<|img_row_2_col_10|>",
287
+ "single_word": false,
288
+ "lstrip": false,
289
+ "rstrip": false,
290
+ "normalized": false,
291
+ "special": true
292
+ },
293
+ "124928": {
294
+ "content": "<|img_row_3_col_1|>",
295
+ "single_word": false,
296
+ "lstrip": false,
297
+ "rstrip": false,
298
+ "normalized": false,
299
+ "special": true
300
+ },
301
+ "124929": {
302
+ "content": "<|img_row_3_col_2|>",
303
+ "single_word": false,
304
+ "lstrip": false,
305
+ "rstrip": false,
306
+ "normalized": false,
307
+ "special": true
308
+ },
309
+ "124930": {
310
+ "content": "<|img_row_3_col_3|>",
311
+ "single_word": false,
312
+ "lstrip": false,
313
+ "rstrip": false,
314
+ "normalized": false,
315
+ "special": true
316
+ },
317
+ "124931": {
318
+ "content": "<|img_row_3_col_4|>",
319
+ "single_word": false,
320
+ "lstrip": false,
321
+ "rstrip": false,
322
+ "normalized": false,
323
+ "special": true
324
+ },
325
+ "124932": {
326
+ "content": "<|img_row_3_col_5|>",
327
+ "single_word": false,
328
+ "lstrip": false,
329
+ "rstrip": false,
330
+ "normalized": false,
331
+ "special": true
332
+ },
333
+ "124933": {
334
+ "content": "<|img_row_3_col_6|>",
335
+ "single_word": false,
336
+ "lstrip": false,
337
+ "rstrip": false,
338
+ "normalized": false,
339
+ "special": true
340
+ },
341
+ "124934": {
342
+ "content": "<|img_row_3_col_7|>",
343
+ "single_word": false,
344
+ "lstrip": false,
345
+ "rstrip": false,
346
+ "normalized": false,
347
+ "special": true
348
+ },
349
+ "124935": {
350
+ "content": "<|img_row_3_col_8|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ "124936": {
358
+ "content": "<|img_row_3_col_9|>",
359
+ "single_word": false,
360
+ "lstrip": false,
361
+ "rstrip": false,
362
+ "normalized": false,
363
+ "special": true
364
+ },
365
+ "124937": {
366
+ "content": "<|img_row_3_col_10|>",
367
+ "single_word": false,
368
+ "lstrip": false,
369
+ "rstrip": false,
370
+ "normalized": false,
371
+ "special": true
372
+ },
373
+ "124938": {
374
+ "content": "<|img_row_4_col_1|>",
375
+ "single_word": false,
376
+ "lstrip": false,
377
+ "rstrip": false,
378
+ "normalized": false,
379
+ "special": true
380
+ },
381
+ "124939": {
382
+ "content": "<|img_row_4_col_2|>",
383
+ "single_word": false,
384
+ "lstrip": false,
385
+ "rstrip": false,
386
+ "normalized": false,
387
+ "special": true
388
+ },
389
+ "124940": {
390
+ "content": "<|img_row_4_col_3|>",
391
+ "single_word": false,
392
+ "lstrip": false,
393
+ "rstrip": false,
394
+ "normalized": false,
395
+ "special": true
396
+ },
397
+ "124941": {
398
+ "content": "<|img_row_4_col_4|>",
399
+ "single_word": false,
400
+ "lstrip": false,
401
+ "rstrip": false,
402
+ "normalized": false,
403
+ "special": true
404
+ },
405
+ "124942": {
406
+ "content": "<|img_row_4_col_5|>",
407
+ "single_word": false,
408
+ "lstrip": false,
409
+ "rstrip": false,
410
+ "normalized": false,
411
+ "special": true
412
+ },
413
+ "124943": {
414
+ "content": "<|img_row_4_col_6|>",
415
+ "single_word": false,
416
+ "lstrip": false,
417
+ "rstrip": false,
418
+ "normalized": false,
419
+ "special": true
420
+ },
421
+ "124944": {
422
+ "content": "<|img_row_4_col_7|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ "124945": {
430
+ "content": "<|img_row_4_col_8|>",
431
+ "single_word": false,
432
+ "lstrip": false,
433
+ "rstrip": false,
434
+ "normalized": false,
435
+ "special": true
436
+ },
437
+ "124946": {
438
+ "content": "<|img_row_4_col_9|>",
439
+ "single_word": false,
440
+ "lstrip": false,
441
+ "rstrip": false,
442
+ "normalized": false,
443
+ "special": true
444
+ },
445
+ "124947": {
446
+ "content": "<|img_row_4_col_10|>",
447
+ "single_word": false,
448
+ "lstrip": false,
449
+ "rstrip": false,
450
+ "normalized": false,
451
+ "special": true
452
+ },
453
+ "124948": {
454
+ "content": "<|img_row_5_col_1|>",
455
+ "single_word": false,
456
+ "lstrip": false,
457
+ "rstrip": false,
458
+ "normalized": false,
459
+ "special": true
460
+ },
461
+ "124949": {
462
+ "content": "<|img_row_5_col_2|>",
463
+ "single_word": false,
464
+ "lstrip": false,
465
+ "rstrip": false,
466
+ "normalized": false,
467
+ "special": true
468
+ },
469
+ "124950": {
470
+ "content": "<|img_row_5_col_3|>",
471
+ "single_word": false,
472
+ "lstrip": false,
473
+ "rstrip": false,
474
+ "normalized": false,
475
+ "special": true
476
+ },
477
+ "124951": {
478
+ "content": "<|img_row_5_col_4|>",
479
+ "single_word": false,
480
+ "lstrip": false,
481
+ "rstrip": false,
482
+ "normalized": false,
483
+ "special": true
484
+ },
485
+ "124952": {
486
+ "content": "<|img_row_5_col_5|>",
487
+ "single_word": false,
488
+ "lstrip": false,
489
+ "rstrip": false,
490
+ "normalized": false,
491
+ "special": true
492
+ },
493
+ "124953": {
494
+ "content": "<|img_row_5_col_6|>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ "124954": {
502
+ "content": "<|img_row_5_col_7|>",
503
+ "single_word": false,
504
+ "lstrip": false,
505
+ "rstrip": false,
506
+ "normalized": false,
507
+ "special": true
508
+ },
509
+ "124955": {
510
+ "content": "<|img_row_5_col_8|>",
511
+ "single_word": false,
512
+ "lstrip": false,
513
+ "rstrip": false,
514
+ "normalized": false,
515
+ "special": true
516
+ },
517
+ "124956": {
518
+ "content": "<|img_row_5_col_9|>",
519
+ "single_word": false,
520
+ "lstrip": false,
521
+ "rstrip": false,
522
+ "normalized": false,
523
+ "special": true
524
+ },
525
+ "124957": {
526
+ "content": "<|img_row_5_col_10|>",
527
+ "single_word": false,
528
+ "lstrip": false,
529
+ "rstrip": false,
530
+ "normalized": false,
531
+ "special": true
532
+ },
533
+ "124958": {
534
+ "content": "<|img_row_6_col_1|>",
535
+ "single_word": false,
536
+ "lstrip": false,
537
+ "rstrip": false,
538
+ "normalized": false,
539
+ "special": true
540
+ },
541
+ "124959": {
542
+ "content": "<|img_row_6_col_2|>",
543
+ "single_word": false,
544
+ "lstrip": false,
545
+ "rstrip": false,
546
+ "normalized": false,
547
+ "special": true
548
+ },
549
+ "124960": {
550
+ "content": "<|img_row_6_col_3|>",
551
+ "single_word": false,
552
+ "lstrip": false,
553
+ "rstrip": false,
554
+ "normalized": false,
555
+ "special": true
556
+ },
557
+ "124961": {
558
+ "content": "<|img_row_6_col_4|>",
559
+ "single_word": false,
560
+ "lstrip": false,
561
+ "rstrip": false,
562
+ "normalized": false,
563
+ "special": true
564
+ },
565
+ "124962": {
566
+ "content": "<|img_row_6_col_5|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ "124963": {
574
+ "content": "<|img_row_6_col_6|>",
575
+ "single_word": false,
576
+ "lstrip": false,
577
+ "rstrip": false,
578
+ "normalized": false,
579
+ "special": true
580
+ },
581
+ "124964": {
582
+ "content": "<|img_row_6_col_7|>",
583
+ "single_word": false,
584
+ "lstrip": false,
585
+ "rstrip": false,
586
+ "normalized": false,
587
+ "special": true
588
+ },
589
+ "124965": {
590
+ "content": "<|img_row_6_col_8|>",
591
+ "single_word": false,
592
+ "lstrip": false,
593
+ "rstrip": false,
594
+ "normalized": false,
595
+ "special": true
596
+ },
597
+ "124966": {
598
+ "content": "<|img_row_6_col_9|>",
599
+ "single_word": false,
600
+ "lstrip": false,
601
+ "rstrip": false,
602
+ "normalized": false,
603
+ "special": true
604
+ },
605
+ "124967": {
606
+ "content": "<|img_row_6_col_10|>",
607
+ "single_word": false,
608
+ "lstrip": false,
609
+ "rstrip": false,
610
+ "normalized": false,
611
+ "special": true
612
+ },
613
+ "124968": {
614
+ "content": "<|img_row_7_col_1|>",
615
+ "single_word": false,
616
+ "lstrip": false,
617
+ "rstrip": false,
618
+ "normalized": false,
619
+ "special": true
620
+ },
621
+ "124969": {
622
+ "content": "<|img_row_7_col_2|>",
623
+ "single_word": false,
624
+ "lstrip": false,
625
+ "rstrip": false,
626
+ "normalized": false,
627
+ "special": true
628
+ },
629
+ "124970": {
630
+ "content": "<|img_row_7_col_3|>",
631
+ "single_word": false,
632
+ "lstrip": false,
633
+ "rstrip": false,
634
+ "normalized": false,
635
+ "special": true
636
+ },
637
+ "124971": {
638
+ "content": "<|img_row_7_col_4|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ "124972": {
646
+ "content": "<|img_row_7_col_5|>",
647
+ "single_word": false,
648
+ "lstrip": false,
649
+ "rstrip": false,
650
+ "normalized": false,
651
+ "special": true
652
+ },
653
+ "124973": {
654
+ "content": "<|img_row_7_col_6|>",
655
+ "single_word": false,
656
+ "lstrip": false,
657
+ "rstrip": false,
658
+ "normalized": false,
659
+ "special": true
660
+ },
661
+ "124974": {
662
+ "content": "<|img_row_7_col_7|>",
663
+ "single_word": false,
664
+ "lstrip": false,
665
+ "rstrip": false,
666
+ "normalized": false,
667
+ "special": true
668
+ },
669
+ "124975": {
670
+ "content": "<|img_row_7_col_8|>",
671
+ "single_word": false,
672
+ "lstrip": false,
673
+ "rstrip": false,
674
+ "normalized": false,
675
+ "special": true
676
+ },
677
+ "124976": {
678
+ "content": "<|img_row_7_col_9|>",
679
+ "single_word": false,
680
+ "lstrip": false,
681
+ "rstrip": false,
682
+ "normalized": false,
683
+ "special": true
684
+ },
685
+ "124977": {
686
+ "content": "<|img_row_7_col_10|>",
687
+ "single_word": false,
688
+ "lstrip": false,
689
+ "rstrip": false,
690
+ "normalized": false,
691
+ "special": true
692
+ },
693
+ "124978": {
694
+ "content": "<|img_row_8_col_1|>",
695
+ "single_word": false,
696
+ "lstrip": false,
697
+ "rstrip": false,
698
+ "normalized": false,
699
+ "special": true
700
+ },
701
+ "124979": {
702
+ "content": "<|img_row_8_col_2|>",
703
+ "single_word": false,
704
+ "lstrip": false,
705
+ "rstrip": false,
706
+ "normalized": false,
707
+ "special": true
708
+ },
709
+ "124980": {
710
+ "content": "<|img_row_8_col_3|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ "124981": {
718
+ "content": "<|img_row_8_col_4|>",
719
+ "single_word": false,
720
+ "lstrip": false,
721
+ "rstrip": false,
722
+ "normalized": false,
723
+ "special": true
724
+ },
725
+ "124982": {
726
+ "content": "<|img_row_8_col_5|>",
727
+ "single_word": false,
728
+ "lstrip": false,
729
+ "rstrip": false,
730
+ "normalized": false,
731
+ "special": true
732
+ },
733
+ "124983": {
734
+ "content": "<|img_row_8_col_6|>",
735
+ "single_word": false,
736
+ "lstrip": false,
737
+ "rstrip": false,
738
+ "normalized": false,
739
+ "special": true
740
+ },
741
+ "124984": {
742
+ "content": "<|img_row_8_col_7|>",
743
+ "single_word": false,
744
+ "lstrip": false,
745
+ "rstrip": false,
746
+ "normalized": false,
747
+ "special": true
748
+ },
749
+ "124985": {
750
+ "content": "<|img_row_8_col_8|>",
751
+ "single_word": false,
752
+ "lstrip": false,
753
+ "rstrip": false,
754
+ "normalized": false,
755
+ "special": true
756
+ },
757
+ "124986": {
758
+ "content": "<|img_row_8_col_9|>",
759
+ "single_word": false,
760
+ "lstrip": false,
761
+ "rstrip": false,
762
+ "normalized": false,
763
+ "special": true
764
+ },
765
+ "124987": {
766
+ "content": "<|img_row_8_col_10|>",
767
+ "single_word": false,
768
+ "lstrip": false,
769
+ "rstrip": false,
770
+ "normalized": false,
771
+ "special": true
772
+ },
773
+ "124988": {
774
+ "content": "<|img_row_9_col_1|>",
775
+ "single_word": false,
776
+ "lstrip": false,
777
+ "rstrip": false,
778
+ "normalized": false,
779
+ "special": true
780
+ },
781
+ "124989": {
782
+ "content": "<|img_row_9_col_2|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ "124990": {
790
+ "content": "<|img_row_9_col_3|>",
791
+ "single_word": false,
792
+ "lstrip": false,
793
+ "rstrip": false,
794
+ "normalized": false,
795
+ "special": true
796
+ },
797
+ "124991": {
798
+ "content": "<|img_row_9_col_4|>",
799
+ "single_word": false,
800
+ "lstrip": false,
801
+ "rstrip": false,
802
+ "normalized": false,
803
+ "special": true
804
+ },
805
+ "124992": {
806
+ "content": "<|img_row_9_col_5|>",
807
+ "single_word": false,
808
+ "lstrip": false,
809
+ "rstrip": false,
810
+ "normalized": false,
811
+ "special": true
812
+ },
813
+ "124993": {
814
+ "content": "<|img_row_9_col_6|>",
815
+ "single_word": false,
816
+ "lstrip": false,
817
+ "rstrip": false,
818
+ "normalized": false,
819
+ "special": true
820
+ },
821
+ "124994": {
822
+ "content": "<|img_row_9_col_7|>",
823
+ "single_word": false,
824
+ "lstrip": false,
825
+ "rstrip": false,
826
+ "normalized": false,
827
+ "special": true
828
+ },
829
+ "124995": {
830
+ "content": "<|img_row_9_col_8|>",
831
+ "single_word": false,
832
+ "lstrip": false,
833
+ "rstrip": false,
834
+ "normalized": false,
835
+ "special": true
836
+ },
837
+ "124996": {
838
+ "content": "<|img_row_9_col_9|>",
839
+ "single_word": false,
840
+ "lstrip": false,
841
+ "rstrip": false,
842
+ "normalized": false,
843
+ "special": true
844
+ },
845
+ "124997": {
846
+ "content": "<|img_row_9_col_10|>",
847
+ "single_word": false,
848
+ "lstrip": false,
849
+ "rstrip": false,
850
+ "normalized": false,
851
+ "special": true
852
+ },
853
+ "124998": {
854
+ "content": "<|img_row_10_col_1|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ "124999": {
862
+ "content": "<|img_row_10_col_2|>",
863
+ "single_word": false,
864
+ "lstrip": false,
865
+ "rstrip": false,
866
+ "normalized": false,
867
+ "special": true
868
+ },
869
+ "125000": {
870
+ "content": "<|img_row_10_col_3|>",
871
+ "single_word": false,
872
+ "lstrip": false,
873
+ "rstrip": false,
874
+ "normalized": false,
875
+ "special": true
876
+ },
877
+ "125001": {
878
+ "content": "<|img_row_10_col_4|>",
879
+ "single_word": false,
880
+ "lstrip": false,
881
+ "rstrip": false,
882
+ "normalized": false,
883
+ "special": true
884
+ },
885
+ "125002": {
886
+ "content": "<|img_row_10_col_5|>",
887
+ "single_word": false,
888
+ "lstrip": false,
889
+ "rstrip": false,
890
+ "normalized": false,
891
+ "special": true
892
+ },
893
+ "125003": {
894
+ "content": "<|img_row_10_col_6|>",
895
+ "single_word": false,
896
+ "lstrip": false,
897
+ "rstrip": false,
898
+ "normalized": false,
899
+ "special": true
900
+ },
901
+ "125004": {
902
+ "content": "<|img_row_10_col_7|>",
903
+ "single_word": false,
904
+ "lstrip": false,
905
+ "rstrip": false,
906
+ "normalized": false,
907
+ "special": true
908
+ },
909
+ "125005": {
910
+ "content": "<|img_row_10_col_8|>",
911
+ "single_word": false,
912
+ "lstrip": false,
913
+ "rstrip": false,
914
+ "normalized": false,
915
+ "special": true
916
+ },
917
+ "125006": {
918
+ "content": "<|img_row_10_col_9|>",
919
+ "single_word": false,
920
+ "lstrip": false,
921
+ "rstrip": false,
922
+ "normalized": false,
923
+ "special": true
924
+ },
925
+ "125007": {
926
+ "content": "<|img_row_10_col_10|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ "125008": {
934
+ "content": "<|img_thumbnail|>",
935
+ "single_word": false,
936
+ "lstrip": false,
937
+ "rstrip": false,
938
+ "normalized": false,
939
+ "special": true
940
+ },
941
+ "125009": {
942
+ "content": "<|image_start|>",
943
+ "single_word": false,
944
+ "lstrip": false,
945
+ "rstrip": false,
946
+ "normalized": false,
947
+ "special": true
948
+ },
949
+ "125010": {
950
+ "content": "<|image_end|>",
951
+ "single_word": false,
952
+ "lstrip": false,
953
+ "rstrip": false,
954
+ "normalized": false,
955
+ "special": true
956
+ },
957
+ "125011": {
958
+ "content": "<|image_split|>",
959
+ "single_word": false,
960
+ "lstrip": false,
961
+ "rstrip": false,
962
+ "normalized": false,
963
+ "special": true
964
+ },
965
+ "125012": {
966
+ "content": "<|audio_start|>",
967
+ "single_word": false,
968
+ "lstrip": false,
969
+ "rstrip": false,
970
+ "normalized": false,
971
+ "special": true
972
+ },
973
+ "125013": {
974
+ "content": "<|text_start|>",
975
+ "single_word": false,
976
+ "lstrip": false,
977
+ "rstrip": false,
978
+ "normalized": false,
979
+ "special": true
980
+ },
981
+ "125014": {
982
+ "content": "<|text_end|>",
983
+ "single_word": false,
984
+ "lstrip": false,
985
+ "rstrip": false,
986
+ "normalized": false,
987
+ "special": true
988
+ },
989
+ "125015": {
990
+ "content": "<|mixed_start|>",
991
+ "single_word": false,
992
+ "lstrip": false,
993
+ "rstrip": false,
994
+ "normalized": false,
995
+ "special": true
996
+ },
997
+ "125016": {
998
+ "content": "<|mixed_end|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ }
1005
+ }
1006
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbc56b39c6b77ac10e3f105b680e6b1746e92e3ec42b1a6489a9880f944877b
3
+ size 5841