Upload LFM2.5-8B-A1B-oQ5 via oMLX
Browse files- .gitattributes +1 -0
- README.md +18 -0
- chat_template.jinja +105 -0
- config.json +741 -0
- generation_config.json +10 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +529 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
.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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
tags:
|
| 4 |
+
- mlx
|
| 5 |
+
- oq
|
| 6 |
+
- quantized
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# LFM2.5-8B-A1B-oQ5
|
| 10 |
+
|
| 11 |
+
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.12) mixed-precision quantization.
|
| 12 |
+
|
| 13 |
+
## Quantization details
|
| 14 |
+
|
| 15 |
+
- **Model type**: lfm2_moe
|
| 16 |
+
- **Bits**: 5
|
| 17 |
+
- **Group size**: 64
|
| 18 |
+
- **Format**: MLX safetensors
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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\n" if ns.system_prompt else "") + "Today's date: " + strftime_now("%Y-%m-%d") + "\n\nList of tools: " + (tools | tojson) -%}
|
| 55 |
+
{%- endif -%}
|
| 56 |
+
{%- if ns.system_prompt -%}
|
| 57 |
+
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
| 58 |
+
{%- endif -%}
|
| 59 |
+
{%- for message in messages -%}
|
| 60 |
+
{%- if message["role"] == "user" -%}
|
| 61 |
+
{%- set ns.last_user_index = loop.index0 -%}
|
| 62 |
+
{%- endif -%}
|
| 63 |
+
{%- endfor -%}
|
| 64 |
+
{%- for message in messages -%}
|
| 65 |
+
{{- "<|im_start|>" + message.role + "\n" -}}
|
| 66 |
+
{%- if message.role == "assistant" -%}
|
| 67 |
+
{%- generation -%}
|
| 68 |
+
{%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 69 |
+
{{- "<think>" + message.thinking + "</think>" -}}
|
| 70 |
+
{%- endif -%}
|
| 71 |
+
{%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
|
| 72 |
+
{%- set _has_cfm = false -%}
|
| 73 |
+
{%- if message.content is defined -%}
|
| 74 |
+
{%- set content = parse_content(message.content) -%}
|
| 75 |
+
{%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 76 |
+
{%- if "</think>" in content -%}
|
| 77 |
+
{%- set content = content.split("</think>")[-1] | trim -%}
|
| 78 |
+
{%- endif -%}
|
| 79 |
+
{%- endif -%}
|
| 80 |
+
{%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
|
| 81 |
+
{%- set _has_cfm = true -%}
|
| 82 |
+
{%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
|
| 83 |
+
{{- content[:_trunc_len] -}}
|
| 84 |
+
{%- else -%}
|
| 85 |
+
{{- content -}}
|
| 86 |
+
{%- endif -%}
|
| 87 |
+
{%- endif -%}
|
| 88 |
+
{%- if message.tool_calls is defined -%}
|
| 89 |
+
{{- render_tool_calls(message.tool_calls) -}}
|
| 90 |
+
{%- endif -%}
|
| 91 |
+
{%- if _has_cfm -%}
|
| 92 |
+
{{- _cfm_tag -}}
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
{{- "<|im_end|>\n" -}}
|
| 95 |
+
{%- endgeneration -%}
|
| 96 |
+
{%- else %}
|
| 97 |
+
{%- if message.get("content") -%}
|
| 98 |
+
{{- parse_content(message["content"]) -}}
|
| 99 |
+
{%- endif -%}
|
| 100 |
+
{{- "<|im_end|>\n" -}}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- endfor -%}
|
| 103 |
+
{%- if add_generation_prompt -%}
|
| 104 |
+
{{- "<|im_start|>assistant\n" -}}
|
| 105 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 124894,
|
| 6 |
+
"conv_L_cache": 3,
|
| 7 |
+
"conv_bias": false,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 124900,
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 7168,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"conv",
|
| 15 |
+
"conv",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"conv",
|
| 18 |
+
"conv",
|
| 19 |
+
"conv",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"conv",
|
| 22 |
+
"conv",
|
| 23 |
+
"conv",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"conv",
|
| 26 |
+
"conv",
|
| 27 |
+
"conv",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"conv",
|
| 30 |
+
"conv",
|
| 31 |
+
"conv",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"conv",
|
| 34 |
+
"conv",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"conv",
|
| 37 |
+
"conv"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 128000,
|
| 40 |
+
"model_type": "lfm2_moe",
|
| 41 |
+
"moe_intermediate_size": 1792,
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_topk_prob": true,
|
| 44 |
+
"num_attention_heads": 32,
|
| 45 |
+
"num_dense_layers": 2,
|
| 46 |
+
"num_experts": 32,
|
| 47 |
+
"num_experts_per_tok": 4,
|
| 48 |
+
"num_hidden_layers": 24,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pad_token_id": 124893,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 5000000,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"routed_scaling_factor": 1.0,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.9.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_expert_bias": true,
|
| 60 |
+
"vocab_size": 128000,
|
| 61 |
+
"quantization": {
|
| 62 |
+
"group_size": 64,
|
| 63 |
+
"bits": 5,
|
| 64 |
+
"mode": "affine",
|
| 65 |
+
"model.embed_tokens": {
|
| 66 |
+
"bits": 8,
|
| 67 |
+
"group_size": 64,
|
| 68 |
+
"mode": "affine"
|
| 69 |
+
},
|
| 70 |
+
"model.layers.0.conv.in_proj": {
|
| 71 |
+
"bits": 8,
|
| 72 |
+
"group_size": 64,
|
| 73 |
+
"mode": "affine"
|
| 74 |
+
},
|
| 75 |
+
"model.layers.0.conv.out_proj": {
|
| 76 |
+
"bits": 8,
|
| 77 |
+
"group_size": 64,
|
| 78 |
+
"mode": "affine"
|
| 79 |
+
},
|
| 80 |
+
"model.layers.0.feed_forward.gate_proj": {
|
| 81 |
+
"bits": 8,
|
| 82 |
+
"group_size": 64,
|
| 83 |
+
"mode": "affine"
|
| 84 |
+
},
|
| 85 |
+
"model.layers.0.feed_forward.down_proj": {
|
| 86 |
+
"bits": 8,
|
| 87 |
+
"group_size": 64,
|
| 88 |
+
"mode": "affine"
|
| 89 |
+
},
|
| 90 |
+
"model.layers.0.feed_forward.up_proj": {
|
| 91 |
+
"bits": 8,
|
| 92 |
+
"group_size": 64,
|
| 93 |
+
"mode": "affine"
|
| 94 |
+
},
|
| 95 |
+
"model.layers.1.conv.in_proj": {
|
| 96 |
+
"bits": 6,
|
| 97 |
+
"group_size": 64,
|
| 98 |
+
"mode": "affine"
|
| 99 |
+
},
|
| 100 |
+
"model.layers.1.conv.out_proj": {
|
| 101 |
+
"bits": 6,
|
| 102 |
+
"group_size": 64,
|
| 103 |
+
"mode": "affine"
|
| 104 |
+
},
|
| 105 |
+
"model.layers.1.feed_forward.gate_proj": {
|
| 106 |
+
"bits": 6,
|
| 107 |
+
"group_size": 64,
|
| 108 |
+
"mode": "affine"
|
| 109 |
+
},
|
| 110 |
+
"model.layers.1.feed_forward.down_proj": {
|
| 111 |
+
"bits": 6,
|
| 112 |
+
"group_size": 64,
|
| 113 |
+
"mode": "affine"
|
| 114 |
+
},
|
| 115 |
+
"model.layers.1.feed_forward.up_proj": {
|
| 116 |
+
"bits": 6,
|
| 117 |
+
"group_size": 64,
|
| 118 |
+
"mode": "affine"
|
| 119 |
+
},
|
| 120 |
+
"model.layers.10.self_attn.k_proj": {
|
| 121 |
+
"bits": 8,
|
| 122 |
+
"group_size": 64,
|
| 123 |
+
"mode": "affine"
|
| 124 |
+
},
|
| 125 |
+
"model.layers.10.self_attn.out_proj": {
|
| 126 |
+
"bits": 8,
|
| 127 |
+
"group_size": 64,
|
| 128 |
+
"mode": "affine"
|
| 129 |
+
},
|
| 130 |
+
"model.layers.10.self_attn.q_proj": {
|
| 131 |
+
"bits": 8,
|
| 132 |
+
"group_size": 64,
|
| 133 |
+
"mode": "affine"
|
| 134 |
+
},
|
| 135 |
+
"model.layers.10.self_attn.v_proj": {
|
| 136 |
+
"bits": 8,
|
| 137 |
+
"group_size": 64,
|
| 138 |
+
"mode": "affine"
|
| 139 |
+
},
|
| 140 |
+
"model.layers.11.conv.in_proj": {
|
| 141 |
+
"bits": 6,
|
| 142 |
+
"group_size": 64,
|
| 143 |
+
"mode": "affine"
|
| 144 |
+
},
|
| 145 |
+
"model.layers.11.conv.out_proj": {
|
| 146 |
+
"bits": 6,
|
| 147 |
+
"group_size": 64,
|
| 148 |
+
"mode": "affine"
|
| 149 |
+
},
|
| 150 |
+
"model.layers.12.conv.in_proj": {
|
| 151 |
+
"bits": 6,
|
| 152 |
+
"group_size": 64,
|
| 153 |
+
"mode": "affine"
|
| 154 |
+
},
|
| 155 |
+
"model.layers.12.conv.out_proj": {
|
| 156 |
+
"bits": 6,
|
| 157 |
+
"group_size": 64,
|
| 158 |
+
"mode": "affine"
|
| 159 |
+
},
|
| 160 |
+
"model.layers.13.conv.in_proj": {
|
| 161 |
+
"bits": 6,
|
| 162 |
+
"group_size": 64,
|
| 163 |
+
"mode": "affine"
|
| 164 |
+
},
|
| 165 |
+
"model.layers.13.conv.out_proj": {
|
| 166 |
+
"bits": 6,
|
| 167 |
+
"group_size": 64,
|
| 168 |
+
"mode": "affine"
|
| 169 |
+
},
|
| 170 |
+
"model.layers.14.self_attn.k_proj": {
|
| 171 |
+
"bits": 8,
|
| 172 |
+
"group_size": 64,
|
| 173 |
+
"mode": "affine"
|
| 174 |
+
},
|
| 175 |
+
"model.layers.14.self_attn.out_proj": {
|
| 176 |
+
"bits": 8,
|
| 177 |
+
"group_size": 64,
|
| 178 |
+
"mode": "affine"
|
| 179 |
+
},
|
| 180 |
+
"model.layers.14.self_attn.q_proj": {
|
| 181 |
+
"bits": 8,
|
| 182 |
+
"group_size": 64,
|
| 183 |
+
"mode": "affine"
|
| 184 |
+
},
|
| 185 |
+
"model.layers.14.self_attn.v_proj": {
|
| 186 |
+
"bits": 8,
|
| 187 |
+
"group_size": 64,
|
| 188 |
+
"mode": "affine"
|
| 189 |
+
},
|
| 190 |
+
"model.layers.15.conv.in_proj": {
|
| 191 |
+
"bits": 6,
|
| 192 |
+
"group_size": 64,
|
| 193 |
+
"mode": "affine"
|
| 194 |
+
},
|
| 195 |
+
"model.layers.15.conv.out_proj": {
|
| 196 |
+
"bits": 6,
|
| 197 |
+
"group_size": 64,
|
| 198 |
+
"mode": "affine"
|
| 199 |
+
},
|
| 200 |
+
"model.layers.16.conv.in_proj": {
|
| 201 |
+
"bits": 6,
|
| 202 |
+
"group_size": 64,
|
| 203 |
+
"mode": "affine"
|
| 204 |
+
},
|
| 205 |
+
"model.layers.16.conv.out_proj": {
|
| 206 |
+
"bits": 6,
|
| 207 |
+
"group_size": 64,
|
| 208 |
+
"mode": "affine"
|
| 209 |
+
},
|
| 210 |
+
"model.layers.17.conv.in_proj": {
|
| 211 |
+
"bits": 6,
|
| 212 |
+
"group_size": 64,
|
| 213 |
+
"mode": "affine"
|
| 214 |
+
},
|
| 215 |
+
"model.layers.17.conv.out_proj": {
|
| 216 |
+
"bits": 6,
|
| 217 |
+
"group_size": 64,
|
| 218 |
+
"mode": "affine"
|
| 219 |
+
},
|
| 220 |
+
"model.layers.18.self_attn.k_proj": {
|
| 221 |
+
"bits": 8,
|
| 222 |
+
"group_size": 64,
|
| 223 |
+
"mode": "affine"
|
| 224 |
+
},
|
| 225 |
+
"model.layers.18.self_attn.out_proj": {
|
| 226 |
+
"bits": 8,
|
| 227 |
+
"group_size": 64,
|
| 228 |
+
"mode": "affine"
|
| 229 |
+
},
|
| 230 |
+
"model.layers.18.self_attn.q_proj": {
|
| 231 |
+
"bits": 8,
|
| 232 |
+
"group_size": 64,
|
| 233 |
+
"mode": "affine"
|
| 234 |
+
},
|
| 235 |
+
"model.layers.18.self_attn.v_proj": {
|
| 236 |
+
"bits": 8,
|
| 237 |
+
"group_size": 64,
|
| 238 |
+
"mode": "affine"
|
| 239 |
+
},
|
| 240 |
+
"model.layers.19.conv.in_proj": {
|
| 241 |
+
"bits": 6,
|
| 242 |
+
"group_size": 64,
|
| 243 |
+
"mode": "affine"
|
| 244 |
+
},
|
| 245 |
+
"model.layers.19.conv.out_proj": {
|
| 246 |
+
"bits": 6,
|
| 247 |
+
"group_size": 64,
|
| 248 |
+
"mode": "affine"
|
| 249 |
+
},
|
| 250 |
+
"model.layers.2.self_attn.k_proj": {
|
| 251 |
+
"bits": 6,
|
| 252 |
+
"group_size": 64,
|
| 253 |
+
"mode": "affine"
|
| 254 |
+
},
|
| 255 |
+
"model.layers.2.self_attn.out_proj": {
|
| 256 |
+
"bits": 6,
|
| 257 |
+
"group_size": 64,
|
| 258 |
+
"mode": "affine"
|
| 259 |
+
},
|
| 260 |
+
"model.layers.2.self_attn.q_proj": {
|
| 261 |
+
"bits": 6,
|
| 262 |
+
"group_size": 64,
|
| 263 |
+
"mode": "affine"
|
| 264 |
+
},
|
| 265 |
+
"model.layers.2.self_attn.v_proj": {
|
| 266 |
+
"bits": 6,
|
| 267 |
+
"group_size": 64,
|
| 268 |
+
"mode": "affine"
|
| 269 |
+
},
|
| 270 |
+
"model.layers.20.conv.in_proj": {
|
| 271 |
+
"bits": 6,
|
| 272 |
+
"group_size": 64,
|
| 273 |
+
"mode": "affine"
|
| 274 |
+
},
|
| 275 |
+
"model.layers.20.conv.out_proj": {
|
| 276 |
+
"bits": 6,
|
| 277 |
+
"group_size": 64,
|
| 278 |
+
"mode": "affine"
|
| 279 |
+
},
|
| 280 |
+
"model.layers.21.self_attn.k_proj": {
|
| 281 |
+
"bits": 8,
|
| 282 |
+
"group_size": 64,
|
| 283 |
+
"mode": "affine"
|
| 284 |
+
},
|
| 285 |
+
"model.layers.21.self_attn.out_proj": {
|
| 286 |
+
"bits": 8,
|
| 287 |
+
"group_size": 64,
|
| 288 |
+
"mode": "affine"
|
| 289 |
+
},
|
| 290 |
+
"model.layers.21.self_attn.q_proj": {
|
| 291 |
+
"bits": 8,
|
| 292 |
+
"group_size": 64,
|
| 293 |
+
"mode": "affine"
|
| 294 |
+
},
|
| 295 |
+
"model.layers.21.self_attn.v_proj": {
|
| 296 |
+
"bits": 8,
|
| 297 |
+
"group_size": 64,
|
| 298 |
+
"mode": "affine"
|
| 299 |
+
},
|
| 300 |
+
"model.layers.22.conv.in_proj": {
|
| 301 |
+
"bits": 6,
|
| 302 |
+
"group_size": 64,
|
| 303 |
+
"mode": "affine"
|
| 304 |
+
},
|
| 305 |
+
"model.layers.22.conv.out_proj": {
|
| 306 |
+
"bits": 6,
|
| 307 |
+
"group_size": 64,
|
| 308 |
+
"mode": "affine"
|
| 309 |
+
},
|
| 310 |
+
"model.layers.23.conv.in_proj": {
|
| 311 |
+
"bits": 6,
|
| 312 |
+
"group_size": 64,
|
| 313 |
+
"mode": "affine"
|
| 314 |
+
},
|
| 315 |
+
"model.layers.23.conv.out_proj": {
|
| 316 |
+
"bits": 6,
|
| 317 |
+
"group_size": 64,
|
| 318 |
+
"mode": "affine"
|
| 319 |
+
},
|
| 320 |
+
"model.layers.3.conv.in_proj": {
|
| 321 |
+
"bits": 6,
|
| 322 |
+
"group_size": 64,
|
| 323 |
+
"mode": "affine"
|
| 324 |
+
},
|
| 325 |
+
"model.layers.3.conv.out_proj": {
|
| 326 |
+
"bits": 6,
|
| 327 |
+
"group_size": 64,
|
| 328 |
+
"mode": "affine"
|
| 329 |
+
},
|
| 330 |
+
"model.layers.4.conv.in_proj": {
|
| 331 |
+
"bits": 6,
|
| 332 |
+
"group_size": 64,
|
| 333 |
+
"mode": "affine"
|
| 334 |
+
},
|
| 335 |
+
"model.layers.4.conv.out_proj": {
|
| 336 |
+
"bits": 6,
|
| 337 |
+
"group_size": 64,
|
| 338 |
+
"mode": "affine"
|
| 339 |
+
},
|
| 340 |
+
"model.layers.5.conv.in_proj": {
|
| 341 |
+
"bits": 6,
|
| 342 |
+
"group_size": 64,
|
| 343 |
+
"mode": "affine"
|
| 344 |
+
},
|
| 345 |
+
"model.layers.5.conv.out_proj": {
|
| 346 |
+
"bits": 6,
|
| 347 |
+
"group_size": 64,
|
| 348 |
+
"mode": "affine"
|
| 349 |
+
},
|
| 350 |
+
"model.layers.6.self_attn.k_proj": {
|
| 351 |
+
"bits": 8,
|
| 352 |
+
"group_size": 64,
|
| 353 |
+
"mode": "affine"
|
| 354 |
+
},
|
| 355 |
+
"model.layers.6.self_attn.out_proj": {
|
| 356 |
+
"bits": 8,
|
| 357 |
+
"group_size": 64,
|
| 358 |
+
"mode": "affine"
|
| 359 |
+
},
|
| 360 |
+
"model.layers.6.self_attn.q_proj": {
|
| 361 |
+
"bits": 8,
|
| 362 |
+
"group_size": 64,
|
| 363 |
+
"mode": "affine"
|
| 364 |
+
},
|
| 365 |
+
"model.layers.6.self_attn.v_proj": {
|
| 366 |
+
"bits": 8,
|
| 367 |
+
"group_size": 64,
|
| 368 |
+
"mode": "affine"
|
| 369 |
+
},
|
| 370 |
+
"model.layers.7.conv.in_proj": {
|
| 371 |
+
"bits": 6,
|
| 372 |
+
"group_size": 64,
|
| 373 |
+
"mode": "affine"
|
| 374 |
+
},
|
| 375 |
+
"model.layers.7.conv.out_proj": {
|
| 376 |
+
"bits": 6,
|
| 377 |
+
"group_size": 64,
|
| 378 |
+
"mode": "affine"
|
| 379 |
+
},
|
| 380 |
+
"model.layers.8.conv.in_proj": {
|
| 381 |
+
"bits": 6,
|
| 382 |
+
"group_size": 64,
|
| 383 |
+
"mode": "affine"
|
| 384 |
+
},
|
| 385 |
+
"model.layers.8.conv.out_proj": {
|
| 386 |
+
"bits": 6,
|
| 387 |
+
"group_size": 64,
|
| 388 |
+
"mode": "affine"
|
| 389 |
+
},
|
| 390 |
+
"model.layers.9.conv.in_proj": {
|
| 391 |
+
"bits": 6,
|
| 392 |
+
"group_size": 64,
|
| 393 |
+
"mode": "affine"
|
| 394 |
+
},
|
| 395 |
+
"model.layers.9.conv.out_proj": {
|
| 396 |
+
"bits": 6,
|
| 397 |
+
"group_size": 64,
|
| 398 |
+
"mode": "affine"
|
| 399 |
+
}
|
| 400 |
+
},
|
| 401 |
+
"quantization_config": {
|
| 402 |
+
"group_size": 64,
|
| 403 |
+
"bits": 5,
|
| 404 |
+
"mode": "affine",
|
| 405 |
+
"model.embed_tokens": {
|
| 406 |
+
"bits": 8,
|
| 407 |
+
"group_size": 64,
|
| 408 |
+
"mode": "affine"
|
| 409 |
+
},
|
| 410 |
+
"model.layers.0.conv.in_proj": {
|
| 411 |
+
"bits": 8,
|
| 412 |
+
"group_size": 64,
|
| 413 |
+
"mode": "affine"
|
| 414 |
+
},
|
| 415 |
+
"model.layers.0.conv.out_proj": {
|
| 416 |
+
"bits": 8,
|
| 417 |
+
"group_size": 64,
|
| 418 |
+
"mode": "affine"
|
| 419 |
+
},
|
| 420 |
+
"model.layers.0.feed_forward.gate_proj": {
|
| 421 |
+
"bits": 8,
|
| 422 |
+
"group_size": 64,
|
| 423 |
+
"mode": "affine"
|
| 424 |
+
},
|
| 425 |
+
"model.layers.0.feed_forward.down_proj": {
|
| 426 |
+
"bits": 8,
|
| 427 |
+
"group_size": 64,
|
| 428 |
+
"mode": "affine"
|
| 429 |
+
},
|
| 430 |
+
"model.layers.0.feed_forward.up_proj": {
|
| 431 |
+
"bits": 8,
|
| 432 |
+
"group_size": 64,
|
| 433 |
+
"mode": "affine"
|
| 434 |
+
},
|
| 435 |
+
"model.layers.1.conv.in_proj": {
|
| 436 |
+
"bits": 6,
|
| 437 |
+
"group_size": 64,
|
| 438 |
+
"mode": "affine"
|
| 439 |
+
},
|
| 440 |
+
"model.layers.1.conv.out_proj": {
|
| 441 |
+
"bits": 6,
|
| 442 |
+
"group_size": 64,
|
| 443 |
+
"mode": "affine"
|
| 444 |
+
},
|
| 445 |
+
"model.layers.1.feed_forward.gate_proj": {
|
| 446 |
+
"bits": 6,
|
| 447 |
+
"group_size": 64,
|
| 448 |
+
"mode": "affine"
|
| 449 |
+
},
|
| 450 |
+
"model.layers.1.feed_forward.down_proj": {
|
| 451 |
+
"bits": 6,
|
| 452 |
+
"group_size": 64,
|
| 453 |
+
"mode": "affine"
|
| 454 |
+
},
|
| 455 |
+
"model.layers.1.feed_forward.up_proj": {
|
| 456 |
+
"bits": 6,
|
| 457 |
+
"group_size": 64,
|
| 458 |
+
"mode": "affine"
|
| 459 |
+
},
|
| 460 |
+
"model.layers.10.self_attn.k_proj": {
|
| 461 |
+
"bits": 8,
|
| 462 |
+
"group_size": 64,
|
| 463 |
+
"mode": "affine"
|
| 464 |
+
},
|
| 465 |
+
"model.layers.10.self_attn.out_proj": {
|
| 466 |
+
"bits": 8,
|
| 467 |
+
"group_size": 64,
|
| 468 |
+
"mode": "affine"
|
| 469 |
+
},
|
| 470 |
+
"model.layers.10.self_attn.q_proj": {
|
| 471 |
+
"bits": 8,
|
| 472 |
+
"group_size": 64,
|
| 473 |
+
"mode": "affine"
|
| 474 |
+
},
|
| 475 |
+
"model.layers.10.self_attn.v_proj": {
|
| 476 |
+
"bits": 8,
|
| 477 |
+
"group_size": 64,
|
| 478 |
+
"mode": "affine"
|
| 479 |
+
},
|
| 480 |
+
"model.layers.11.conv.in_proj": {
|
| 481 |
+
"bits": 6,
|
| 482 |
+
"group_size": 64,
|
| 483 |
+
"mode": "affine"
|
| 484 |
+
},
|
| 485 |
+
"model.layers.11.conv.out_proj": {
|
| 486 |
+
"bits": 6,
|
| 487 |
+
"group_size": 64,
|
| 488 |
+
"mode": "affine"
|
| 489 |
+
},
|
| 490 |
+
"model.layers.12.conv.in_proj": {
|
| 491 |
+
"bits": 6,
|
| 492 |
+
"group_size": 64,
|
| 493 |
+
"mode": "affine"
|
| 494 |
+
},
|
| 495 |
+
"model.layers.12.conv.out_proj": {
|
| 496 |
+
"bits": 6,
|
| 497 |
+
"group_size": 64,
|
| 498 |
+
"mode": "affine"
|
| 499 |
+
},
|
| 500 |
+
"model.layers.13.conv.in_proj": {
|
| 501 |
+
"bits": 6,
|
| 502 |
+
"group_size": 64,
|
| 503 |
+
"mode": "affine"
|
| 504 |
+
},
|
| 505 |
+
"model.layers.13.conv.out_proj": {
|
| 506 |
+
"bits": 6,
|
| 507 |
+
"group_size": 64,
|
| 508 |
+
"mode": "affine"
|
| 509 |
+
},
|
| 510 |
+
"model.layers.14.self_attn.k_proj": {
|
| 511 |
+
"bits": 8,
|
| 512 |
+
"group_size": 64,
|
| 513 |
+
"mode": "affine"
|
| 514 |
+
},
|
| 515 |
+
"model.layers.14.self_attn.out_proj": {
|
| 516 |
+
"bits": 8,
|
| 517 |
+
"group_size": 64,
|
| 518 |
+
"mode": "affine"
|
| 519 |
+
},
|
| 520 |
+
"model.layers.14.self_attn.q_proj": {
|
| 521 |
+
"bits": 8,
|
| 522 |
+
"group_size": 64,
|
| 523 |
+
"mode": "affine"
|
| 524 |
+
},
|
| 525 |
+
"model.layers.14.self_attn.v_proj": {
|
| 526 |
+
"bits": 8,
|
| 527 |
+
"group_size": 64,
|
| 528 |
+
"mode": "affine"
|
| 529 |
+
},
|
| 530 |
+
"model.layers.15.conv.in_proj": {
|
| 531 |
+
"bits": 6,
|
| 532 |
+
"group_size": 64,
|
| 533 |
+
"mode": "affine"
|
| 534 |
+
},
|
| 535 |
+
"model.layers.15.conv.out_proj": {
|
| 536 |
+
"bits": 6,
|
| 537 |
+
"group_size": 64,
|
| 538 |
+
"mode": "affine"
|
| 539 |
+
},
|
| 540 |
+
"model.layers.16.conv.in_proj": {
|
| 541 |
+
"bits": 6,
|
| 542 |
+
"group_size": 64,
|
| 543 |
+
"mode": "affine"
|
| 544 |
+
},
|
| 545 |
+
"model.layers.16.conv.out_proj": {
|
| 546 |
+
"bits": 6,
|
| 547 |
+
"group_size": 64,
|
| 548 |
+
"mode": "affine"
|
| 549 |
+
},
|
| 550 |
+
"model.layers.17.conv.in_proj": {
|
| 551 |
+
"bits": 6,
|
| 552 |
+
"group_size": 64,
|
| 553 |
+
"mode": "affine"
|
| 554 |
+
},
|
| 555 |
+
"model.layers.17.conv.out_proj": {
|
| 556 |
+
"bits": 6,
|
| 557 |
+
"group_size": 64,
|
| 558 |
+
"mode": "affine"
|
| 559 |
+
},
|
| 560 |
+
"model.layers.18.self_attn.k_proj": {
|
| 561 |
+
"bits": 8,
|
| 562 |
+
"group_size": 64,
|
| 563 |
+
"mode": "affine"
|
| 564 |
+
},
|
| 565 |
+
"model.layers.18.self_attn.out_proj": {
|
| 566 |
+
"bits": 8,
|
| 567 |
+
"group_size": 64,
|
| 568 |
+
"mode": "affine"
|
| 569 |
+
},
|
| 570 |
+
"model.layers.18.self_attn.q_proj": {
|
| 571 |
+
"bits": 8,
|
| 572 |
+
"group_size": 64,
|
| 573 |
+
"mode": "affine"
|
| 574 |
+
},
|
| 575 |
+
"model.layers.18.self_attn.v_proj": {
|
| 576 |
+
"bits": 8,
|
| 577 |
+
"group_size": 64,
|
| 578 |
+
"mode": "affine"
|
| 579 |
+
},
|
| 580 |
+
"model.layers.19.conv.in_proj": {
|
| 581 |
+
"bits": 6,
|
| 582 |
+
"group_size": 64,
|
| 583 |
+
"mode": "affine"
|
| 584 |
+
},
|
| 585 |
+
"model.layers.19.conv.out_proj": {
|
| 586 |
+
"bits": 6,
|
| 587 |
+
"group_size": 64,
|
| 588 |
+
"mode": "affine"
|
| 589 |
+
},
|
| 590 |
+
"model.layers.2.self_attn.k_proj": {
|
| 591 |
+
"bits": 6,
|
| 592 |
+
"group_size": 64,
|
| 593 |
+
"mode": "affine"
|
| 594 |
+
},
|
| 595 |
+
"model.layers.2.self_attn.out_proj": {
|
| 596 |
+
"bits": 6,
|
| 597 |
+
"group_size": 64,
|
| 598 |
+
"mode": "affine"
|
| 599 |
+
},
|
| 600 |
+
"model.layers.2.self_attn.q_proj": {
|
| 601 |
+
"bits": 6,
|
| 602 |
+
"group_size": 64,
|
| 603 |
+
"mode": "affine"
|
| 604 |
+
},
|
| 605 |
+
"model.layers.2.self_attn.v_proj": {
|
| 606 |
+
"bits": 6,
|
| 607 |
+
"group_size": 64,
|
| 608 |
+
"mode": "affine"
|
| 609 |
+
},
|
| 610 |
+
"model.layers.20.conv.in_proj": {
|
| 611 |
+
"bits": 6,
|
| 612 |
+
"group_size": 64,
|
| 613 |
+
"mode": "affine"
|
| 614 |
+
},
|
| 615 |
+
"model.layers.20.conv.out_proj": {
|
| 616 |
+
"bits": 6,
|
| 617 |
+
"group_size": 64,
|
| 618 |
+
"mode": "affine"
|
| 619 |
+
},
|
| 620 |
+
"model.layers.21.self_attn.k_proj": {
|
| 621 |
+
"bits": 8,
|
| 622 |
+
"group_size": 64,
|
| 623 |
+
"mode": "affine"
|
| 624 |
+
},
|
| 625 |
+
"model.layers.21.self_attn.out_proj": {
|
| 626 |
+
"bits": 8,
|
| 627 |
+
"group_size": 64,
|
| 628 |
+
"mode": "affine"
|
| 629 |
+
},
|
| 630 |
+
"model.layers.21.self_attn.q_proj": {
|
| 631 |
+
"bits": 8,
|
| 632 |
+
"group_size": 64,
|
| 633 |
+
"mode": "affine"
|
| 634 |
+
},
|
| 635 |
+
"model.layers.21.self_attn.v_proj": {
|
| 636 |
+
"bits": 8,
|
| 637 |
+
"group_size": 64,
|
| 638 |
+
"mode": "affine"
|
| 639 |
+
},
|
| 640 |
+
"model.layers.22.conv.in_proj": {
|
| 641 |
+
"bits": 6,
|
| 642 |
+
"group_size": 64,
|
| 643 |
+
"mode": "affine"
|
| 644 |
+
},
|
| 645 |
+
"model.layers.22.conv.out_proj": {
|
| 646 |
+
"bits": 6,
|
| 647 |
+
"group_size": 64,
|
| 648 |
+
"mode": "affine"
|
| 649 |
+
},
|
| 650 |
+
"model.layers.23.conv.in_proj": {
|
| 651 |
+
"bits": 6,
|
| 652 |
+
"group_size": 64,
|
| 653 |
+
"mode": "affine"
|
| 654 |
+
},
|
| 655 |
+
"model.layers.23.conv.out_proj": {
|
| 656 |
+
"bits": 6,
|
| 657 |
+
"group_size": 64,
|
| 658 |
+
"mode": "affine"
|
| 659 |
+
},
|
| 660 |
+
"model.layers.3.conv.in_proj": {
|
| 661 |
+
"bits": 6,
|
| 662 |
+
"group_size": 64,
|
| 663 |
+
"mode": "affine"
|
| 664 |
+
},
|
| 665 |
+
"model.layers.3.conv.out_proj": {
|
| 666 |
+
"bits": 6,
|
| 667 |
+
"group_size": 64,
|
| 668 |
+
"mode": "affine"
|
| 669 |
+
},
|
| 670 |
+
"model.layers.4.conv.in_proj": {
|
| 671 |
+
"bits": 6,
|
| 672 |
+
"group_size": 64,
|
| 673 |
+
"mode": "affine"
|
| 674 |
+
},
|
| 675 |
+
"model.layers.4.conv.out_proj": {
|
| 676 |
+
"bits": 6,
|
| 677 |
+
"group_size": 64,
|
| 678 |
+
"mode": "affine"
|
| 679 |
+
},
|
| 680 |
+
"model.layers.5.conv.in_proj": {
|
| 681 |
+
"bits": 6,
|
| 682 |
+
"group_size": 64,
|
| 683 |
+
"mode": "affine"
|
| 684 |
+
},
|
| 685 |
+
"model.layers.5.conv.out_proj": {
|
| 686 |
+
"bits": 6,
|
| 687 |
+
"group_size": 64,
|
| 688 |
+
"mode": "affine"
|
| 689 |
+
},
|
| 690 |
+
"model.layers.6.self_attn.k_proj": {
|
| 691 |
+
"bits": 8,
|
| 692 |
+
"group_size": 64,
|
| 693 |
+
"mode": "affine"
|
| 694 |
+
},
|
| 695 |
+
"model.layers.6.self_attn.out_proj": {
|
| 696 |
+
"bits": 8,
|
| 697 |
+
"group_size": 64,
|
| 698 |
+
"mode": "affine"
|
| 699 |
+
},
|
| 700 |
+
"model.layers.6.self_attn.q_proj": {
|
| 701 |
+
"bits": 8,
|
| 702 |
+
"group_size": 64,
|
| 703 |
+
"mode": "affine"
|
| 704 |
+
},
|
| 705 |
+
"model.layers.6.self_attn.v_proj": {
|
| 706 |
+
"bits": 8,
|
| 707 |
+
"group_size": 64,
|
| 708 |
+
"mode": "affine"
|
| 709 |
+
},
|
| 710 |
+
"model.layers.7.conv.in_proj": {
|
| 711 |
+
"bits": 6,
|
| 712 |
+
"group_size": 64,
|
| 713 |
+
"mode": "affine"
|
| 714 |
+
},
|
| 715 |
+
"model.layers.7.conv.out_proj": {
|
| 716 |
+
"bits": 6,
|
| 717 |
+
"group_size": 64,
|
| 718 |
+
"mode": "affine"
|
| 719 |
+
},
|
| 720 |
+
"model.layers.8.conv.in_proj": {
|
| 721 |
+
"bits": 6,
|
| 722 |
+
"group_size": 64,
|
| 723 |
+
"mode": "affine"
|
| 724 |
+
},
|
| 725 |
+
"model.layers.8.conv.out_proj": {
|
| 726 |
+
"bits": 6,
|
| 727 |
+
"group_size": 64,
|
| 728 |
+
"mode": "affine"
|
| 729 |
+
},
|
| 730 |
+
"model.layers.9.conv.in_proj": {
|
| 731 |
+
"bits": 6,
|
| 732 |
+
"group_size": 64,
|
| 733 |
+
"mode": "affine"
|
| 734 |
+
},
|
| 735 |
+
"model.layers.9.conv.out_proj": {
|
| 736 |
+
"bits": 6,
|
| 737 |
+
"group_size": 64,
|
| 738 |
+
"mode": "affine"
|
| 739 |
+
}
|
| 740 |
+
}
|
| 741 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 124894,
|
| 4 |
+
"eos_token_id": 124900,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 124893,
|
| 8 |
+
"transformers_version": "5.9.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34a9d484601af632abd53f2c80dcd7361d4b44c940224013877c88e71e0a5df
|
| 3 |
+
size 5038235503
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c03a460735ed65b3e2f2fe82f05d762ba9b311bb4e823bfd176f4f060c073e3
|
| 3 |
+
size 968889037
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6007124540
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.biases": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.scales": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.embedding_norm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.1.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.1.feed_forward.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.1.feed_forward.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.1.feed_forward.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.1.feed_forward.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.1.feed_forward.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.1.feed_forward.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.10.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.10.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.10.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.10.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.10.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.10.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.10.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.10.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.10.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.10.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.10.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.10.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.11.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.11.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.11.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.11.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.11.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.11.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.11.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.11.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.11.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.11.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.11.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.11.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.11.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.12.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.12.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.12.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.12.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.12.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.12.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.12.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.12.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.12.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.12.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.12.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.12.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.12.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.12.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.12.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.12.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.13.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.13.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.13.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.13.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.13.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.13.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.13.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.13.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.13.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.13.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.13.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.13.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.13.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.13.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.13.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.13.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.14.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.14.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.14.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.14.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.14.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.14.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.14.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.14.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.14.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.14.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.14.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.14.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.14.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.15.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.15.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.15.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.15.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.15.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.15.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.15.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.15.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.15.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.15.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.15.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.15.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.15.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.15.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.16.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.16.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.16.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.16.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.16.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.16.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.16.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.16.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.16.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.16.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.16.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.16.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.16.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.16.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.16.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.16.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.16.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.17.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.17.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.17.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.17.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.17.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.17.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.17.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.17.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.17.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.17.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.17.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.17.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.17.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.17.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.17.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.17.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.17.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.18.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.18.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.18.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.18.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.18.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.18.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.18.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.18.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.18.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.18.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.18.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.18.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.18.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.18.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.19.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.19.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.19.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.19.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.19.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.19.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.19.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.19.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.19.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.19.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.19.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.19.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.19.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.19.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.19.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.19.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.19.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.2.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.2.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.2.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.2.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.2.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.2.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.2.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.2.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.2.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.2.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.2.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.2.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.20.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.20.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.20.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.20.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.20.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.20.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.20.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.20.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.20.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.20.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.20.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.20.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.20.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.20.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.20.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.20.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.20.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.21.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.21.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.21.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.21.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.21.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.21.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.21.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.21.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.21.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.21.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.21.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.21.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.21.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.21.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.22.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.22.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.22.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.22.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.22.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.22.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.22.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.22.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.22.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.22.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.22.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.22.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.22.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.22.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.22.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.22.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.22.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.23.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.23.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.23.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.23.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.23.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.23.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.23.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.23.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.23.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.23.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.23.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.23.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.layers.23.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 376 |
+
"model.layers.23.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 377 |
+
"model.layers.23.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.layers.23.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 379 |
+
"model.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.23.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.3.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.3.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.3.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.3.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.3.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.3.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.3.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.3.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.3.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.3.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.3.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.3.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.3.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.3.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.3.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.3.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.3.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.4.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.4.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.4.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.4.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.4.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.4.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.4.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.4.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.4.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.4.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.4.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.4.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.4.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.4.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.4.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.4.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.4.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.5.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.5.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.5.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.5.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.5.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.5.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.5.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.5.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.5.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.5.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.5.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.5.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.5.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.5.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.5.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.5.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.5.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.6.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.6.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.6.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.6.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.6.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.6.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.6.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.6.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.6.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.6.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.6.self_attn.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.6.self_attn.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.7.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.7.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.7.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.7.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.7.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.7.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.7.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.7.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.7.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.7.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.7.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.7.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.7.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.7.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.7.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.7.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.8.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.8.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.8.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.8.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.8.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.8.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.8.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.8.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.8.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.8.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.8.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.8.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.8.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.8.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.8.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.8.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.8.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.9.conv.conv.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.9.conv.in_proj.biases": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.9.conv.in_proj.scales": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.9.conv.in_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.9.conv.out_proj.biases": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.9.conv.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.9.conv.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.9.feed_forward.expert_bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.9.feed_forward.gate.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.9.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.9.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.9.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.9.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.9.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.9.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.9.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.9.operator_norm.weight": "model-00001-of-00002.safetensors"
|
| 528 |
+
}
|
| 529 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4687c0046da6579aba6f9aa713e9bed61e5fd210b0e012028ae57751d028689
|
| 3 |
+
size 17905589
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|startoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"legacy": false,
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "<|pad|>",
|
| 10 |
+
"tokenizer_class": "TokenizersBackend",
|
| 11 |
+
"use_default_system_prompt": false
|
| 12 |
+
}
|