Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +31 -0
- added_tokens.json +28 -0
- chat_template.jinja +117 -0
- config.json +433 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +1021 -0
- qwen3coder_tool_parser.py +689 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
license_link: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- mlx
|
| 8 |
+
- qwen
|
| 9 |
+
- coder
|
| 10 |
+
- 4bit
|
| 11 |
+
- mxfp4
|
| 12 |
+
base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Qwen3-Coder-30B-A3B-Instruct (MLX, 4-bit, mxfp4)
|
| 16 |
+
|
| 17 |
+
This model is an MLX-converted version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), optimized for Apple Silicon.
|
| 18 |
+
It uses 4-bit quantization with the following settings:
|
| 19 |
+
- **Quantization**: 4-bit with `--q-mode mxfp4` for efficient performance on Apple Silicon.
|
| 20 |
+
- **Group size**: 32 (`--q-group-size 32`) for improved precision with moderate memory usage (~22-27 GB).
|
| 21 |
+
- **Context**: Supports up to 262k tokens natively, optimized for agentic coding tasks and large-scale code repository analysis.
|
| 22 |
+
|
| 23 |
+
## Conversion Command
|
| 24 |
+
```bash
|
| 25 |
+
mlx_lm.convert \
|
| 26 |
+
--hf-path Qwen/Qwen3-Coder-30B-A3B-Instruct \
|
| 27 |
+
-q \
|
| 28 |
+
--q-bits 4 \
|
| 29 |
+
--q-mode mxfp4 \
|
| 30 |
+
--q-group-size 32 \
|
| 31 |
+
--mlx-path ./qwen3-coder-30b-mlx
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 5 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{% endmacro %}
|
| 12 |
+
|
| 13 |
+
{%- if messages[0]["role"] == "system" %}
|
| 14 |
+
{%- set system_message = messages[0]["content"] %}
|
| 15 |
+
{%- set loop_messages = messages[1:] %}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- set loop_messages = messages %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
|
| 20 |
+
{%- if not tools is defined %}
|
| 21 |
+
{%- set tools = [] %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- if system_message is defined %}
|
| 25 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 28 |
+
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 32 |
+
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 33 |
+
{{- "<tools>" }}
|
| 34 |
+
{%- for tool in tools %}
|
| 35 |
+
{%- if tool.function is defined %}
|
| 36 |
+
{%- set tool = tool.function %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 39 |
+
{%- if tool.description is defined %}
|
| 40 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '\n<parameters>' }}
|
| 43 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 44 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 45 |
+
{{- '\n<parameter>' }}
|
| 46 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 47 |
+
{%- if param_fields.type is defined %}
|
| 48 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if param_fields.description is defined %}
|
| 51 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 54 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 55 |
+
{{- '\n</parameter>' }}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{% set handled_keys = ['type', 'properties'] %}
|
| 59 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 60 |
+
{{- '\n</parameters>' }}
|
| 61 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 62 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 63 |
+
{{- '\n</function>' }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if system_message is defined %}
|
| 69 |
+
{{- '<|im_end|>\n' }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 72 |
+
{{- '<|im_end|>\n' }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- for message in loop_messages %}
|
| 76 |
+
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 77 |
+
{{- '<|im_start|>' + message.role }}
|
| 78 |
+
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
| 79 |
+
{{- '\n' + message.content | trim + '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for tool_call in message.tool_calls %}
|
| 82 |
+
{%- if tool_call.function is defined %}
|
| 83 |
+
{%- set tool_call = tool_call.function %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 86 |
+
{%- if tool_call.arguments is defined %}
|
| 87 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 88 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 89 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 90 |
+
{{- args_value }}
|
| 91 |
+
{{- '\n</parameter>\n' }}
|
| 92 |
+
{%- endfor %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '</function>\n</tool_call>' }}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{{- '<|im_end|>\n' }}
|
| 97 |
+
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
| 98 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 99 |
+
{%- elif message.role == "tool" %}
|
| 100 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 101 |
+
{{- '<|im_start|>user\n' }}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '<tool_response>\n' }}
|
| 104 |
+
{{- message.content }}
|
| 105 |
+
{{- '\n</tool_response>\n' }}
|
| 106 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 107 |
+
{{- '<|im_end|>\n' }}
|
| 108 |
+
{%- elif loop.last %}
|
| 109 |
+
{{- '<|im_end|>\n' }}
|
| 110 |
+
{%- endif %}
|
| 111 |
+
{%- else %}
|
| 112 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 113 |
+
{%- endif %}
|
| 114 |
+
{%- endfor %}
|
| 115 |
+
{%- if add_generation_prompt %}
|
| 116 |
+
{{- '<|im_start|>assistant\n' }}
|
| 117 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"decoder_sparse_step": 1,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 5472,
|
| 13 |
+
"max_position_embeddings": 262144,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"mlp_only_layers": [],
|
| 16 |
+
"model_type": "qwen3_moe",
|
| 17 |
+
"moe_intermediate_size": 768,
|
| 18 |
+
"norm_topk_prob": true,
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_experts": 128,
|
| 21 |
+
"num_experts_per_tok": 8,
|
| 22 |
+
"num_hidden_layers": 48,
|
| 23 |
+
"num_key_value_heads": 4,
|
| 24 |
+
"output_router_logits": false,
|
| 25 |
+
"qkv_bias": false,
|
| 26 |
+
"quantization": {
|
| 27 |
+
"group_size": 32,
|
| 28 |
+
"bits": 4,
|
| 29 |
+
"mode": "mxfp4",
|
| 30 |
+
"model.layers.0.mlp.gate": {
|
| 31 |
+
"group_size": 64,
|
| 32 |
+
"bits": 8
|
| 33 |
+
},
|
| 34 |
+
"model.layers.1.mlp.gate": {
|
| 35 |
+
"group_size": 64,
|
| 36 |
+
"bits": 8
|
| 37 |
+
},
|
| 38 |
+
"model.layers.2.mlp.gate": {
|
| 39 |
+
"group_size": 64,
|
| 40 |
+
"bits": 8
|
| 41 |
+
},
|
| 42 |
+
"model.layers.3.mlp.gate": {
|
| 43 |
+
"group_size": 64,
|
| 44 |
+
"bits": 8
|
| 45 |
+
},
|
| 46 |
+
"model.layers.4.mlp.gate": {
|
| 47 |
+
"group_size": 64,
|
| 48 |
+
"bits": 8
|
| 49 |
+
},
|
| 50 |
+
"model.layers.5.mlp.gate": {
|
| 51 |
+
"group_size": 64,
|
| 52 |
+
"bits": 8
|
| 53 |
+
},
|
| 54 |
+
"model.layers.6.mlp.gate": {
|
| 55 |
+
"group_size": 64,
|
| 56 |
+
"bits": 8
|
| 57 |
+
},
|
| 58 |
+
"model.layers.7.mlp.gate": {
|
| 59 |
+
"group_size": 64,
|
| 60 |
+
"bits": 8
|
| 61 |
+
},
|
| 62 |
+
"model.layers.8.mlp.gate": {
|
| 63 |
+
"group_size": 64,
|
| 64 |
+
"bits": 8
|
| 65 |
+
},
|
| 66 |
+
"model.layers.9.mlp.gate": {
|
| 67 |
+
"group_size": 64,
|
| 68 |
+
"bits": 8
|
| 69 |
+
},
|
| 70 |
+
"model.layers.10.mlp.gate": {
|
| 71 |
+
"group_size": 64,
|
| 72 |
+
"bits": 8
|
| 73 |
+
},
|
| 74 |
+
"model.layers.11.mlp.gate": {
|
| 75 |
+
"group_size": 64,
|
| 76 |
+
"bits": 8
|
| 77 |
+
},
|
| 78 |
+
"model.layers.12.mlp.gate": {
|
| 79 |
+
"group_size": 64,
|
| 80 |
+
"bits": 8
|
| 81 |
+
},
|
| 82 |
+
"model.layers.13.mlp.gate": {
|
| 83 |
+
"group_size": 64,
|
| 84 |
+
"bits": 8
|
| 85 |
+
},
|
| 86 |
+
"model.layers.14.mlp.gate": {
|
| 87 |
+
"group_size": 64,
|
| 88 |
+
"bits": 8
|
| 89 |
+
},
|
| 90 |
+
"model.layers.15.mlp.gate": {
|
| 91 |
+
"group_size": 64,
|
| 92 |
+
"bits": 8
|
| 93 |
+
},
|
| 94 |
+
"model.layers.16.mlp.gate": {
|
| 95 |
+
"group_size": 64,
|
| 96 |
+
"bits": 8
|
| 97 |
+
},
|
| 98 |
+
"model.layers.17.mlp.gate": {
|
| 99 |
+
"group_size": 64,
|
| 100 |
+
"bits": 8
|
| 101 |
+
},
|
| 102 |
+
"model.layers.18.mlp.gate": {
|
| 103 |
+
"group_size": 64,
|
| 104 |
+
"bits": 8
|
| 105 |
+
},
|
| 106 |
+
"model.layers.19.mlp.gate": {
|
| 107 |
+
"group_size": 64,
|
| 108 |
+
"bits": 8
|
| 109 |
+
},
|
| 110 |
+
"model.layers.20.mlp.gate": {
|
| 111 |
+
"group_size": 64,
|
| 112 |
+
"bits": 8
|
| 113 |
+
},
|
| 114 |
+
"model.layers.21.mlp.gate": {
|
| 115 |
+
"group_size": 64,
|
| 116 |
+
"bits": 8
|
| 117 |
+
},
|
| 118 |
+
"model.layers.22.mlp.gate": {
|
| 119 |
+
"group_size": 64,
|
| 120 |
+
"bits": 8
|
| 121 |
+
},
|
| 122 |
+
"model.layers.23.mlp.gate": {
|
| 123 |
+
"group_size": 64,
|
| 124 |
+
"bits": 8
|
| 125 |
+
},
|
| 126 |
+
"model.layers.24.mlp.gate": {
|
| 127 |
+
"group_size": 64,
|
| 128 |
+
"bits": 8
|
| 129 |
+
},
|
| 130 |
+
"model.layers.25.mlp.gate": {
|
| 131 |
+
"group_size": 64,
|
| 132 |
+
"bits": 8
|
| 133 |
+
},
|
| 134 |
+
"model.layers.26.mlp.gate": {
|
| 135 |
+
"group_size": 64,
|
| 136 |
+
"bits": 8
|
| 137 |
+
},
|
| 138 |
+
"model.layers.27.mlp.gate": {
|
| 139 |
+
"group_size": 64,
|
| 140 |
+
"bits": 8
|
| 141 |
+
},
|
| 142 |
+
"model.layers.28.mlp.gate": {
|
| 143 |
+
"group_size": 64,
|
| 144 |
+
"bits": 8
|
| 145 |
+
},
|
| 146 |
+
"model.layers.29.mlp.gate": {
|
| 147 |
+
"group_size": 64,
|
| 148 |
+
"bits": 8
|
| 149 |
+
},
|
| 150 |
+
"model.layers.30.mlp.gate": {
|
| 151 |
+
"group_size": 64,
|
| 152 |
+
"bits": 8
|
| 153 |
+
},
|
| 154 |
+
"model.layers.31.mlp.gate": {
|
| 155 |
+
"group_size": 64,
|
| 156 |
+
"bits": 8
|
| 157 |
+
},
|
| 158 |
+
"model.layers.32.mlp.gate": {
|
| 159 |
+
"group_size": 64,
|
| 160 |
+
"bits": 8
|
| 161 |
+
},
|
| 162 |
+
"model.layers.33.mlp.gate": {
|
| 163 |
+
"group_size": 64,
|
| 164 |
+
"bits": 8
|
| 165 |
+
},
|
| 166 |
+
"model.layers.34.mlp.gate": {
|
| 167 |
+
"group_size": 64,
|
| 168 |
+
"bits": 8
|
| 169 |
+
},
|
| 170 |
+
"model.layers.35.mlp.gate": {
|
| 171 |
+
"group_size": 64,
|
| 172 |
+
"bits": 8
|
| 173 |
+
},
|
| 174 |
+
"model.layers.36.mlp.gate": {
|
| 175 |
+
"group_size": 64,
|
| 176 |
+
"bits": 8
|
| 177 |
+
},
|
| 178 |
+
"model.layers.37.mlp.gate": {
|
| 179 |
+
"group_size": 64,
|
| 180 |
+
"bits": 8
|
| 181 |
+
},
|
| 182 |
+
"model.layers.38.mlp.gate": {
|
| 183 |
+
"group_size": 64,
|
| 184 |
+
"bits": 8
|
| 185 |
+
},
|
| 186 |
+
"model.layers.39.mlp.gate": {
|
| 187 |
+
"group_size": 64,
|
| 188 |
+
"bits": 8
|
| 189 |
+
},
|
| 190 |
+
"model.layers.40.mlp.gate": {
|
| 191 |
+
"group_size": 64,
|
| 192 |
+
"bits": 8
|
| 193 |
+
},
|
| 194 |
+
"model.layers.41.mlp.gate": {
|
| 195 |
+
"group_size": 64,
|
| 196 |
+
"bits": 8
|
| 197 |
+
},
|
| 198 |
+
"model.layers.42.mlp.gate": {
|
| 199 |
+
"group_size": 64,
|
| 200 |
+
"bits": 8
|
| 201 |
+
},
|
| 202 |
+
"model.layers.43.mlp.gate": {
|
| 203 |
+
"group_size": 64,
|
| 204 |
+
"bits": 8
|
| 205 |
+
},
|
| 206 |
+
"model.layers.44.mlp.gate": {
|
| 207 |
+
"group_size": 64,
|
| 208 |
+
"bits": 8
|
| 209 |
+
},
|
| 210 |
+
"model.layers.45.mlp.gate": {
|
| 211 |
+
"group_size": 64,
|
| 212 |
+
"bits": 8
|
| 213 |
+
},
|
| 214 |
+
"model.layers.46.mlp.gate": {
|
| 215 |
+
"group_size": 64,
|
| 216 |
+
"bits": 8
|
| 217 |
+
},
|
| 218 |
+
"model.layers.47.mlp.gate": {
|
| 219 |
+
"group_size": 64,
|
| 220 |
+
"bits": 8
|
| 221 |
+
}
|
| 222 |
+
},
|
| 223 |
+
"quantization_config": {
|
| 224 |
+
"group_size": 32,
|
| 225 |
+
"bits": 4,
|
| 226 |
+
"mode": "mxfp4",
|
| 227 |
+
"model.layers.0.mlp.gate": {
|
| 228 |
+
"group_size": 64,
|
| 229 |
+
"bits": 8
|
| 230 |
+
},
|
| 231 |
+
"model.layers.1.mlp.gate": {
|
| 232 |
+
"group_size": 64,
|
| 233 |
+
"bits": 8
|
| 234 |
+
},
|
| 235 |
+
"model.layers.2.mlp.gate": {
|
| 236 |
+
"group_size": 64,
|
| 237 |
+
"bits": 8
|
| 238 |
+
},
|
| 239 |
+
"model.layers.3.mlp.gate": {
|
| 240 |
+
"group_size": 64,
|
| 241 |
+
"bits": 8
|
| 242 |
+
},
|
| 243 |
+
"model.layers.4.mlp.gate": {
|
| 244 |
+
"group_size": 64,
|
| 245 |
+
"bits": 8
|
| 246 |
+
},
|
| 247 |
+
"model.layers.5.mlp.gate": {
|
| 248 |
+
"group_size": 64,
|
| 249 |
+
"bits": 8
|
| 250 |
+
},
|
| 251 |
+
"model.layers.6.mlp.gate": {
|
| 252 |
+
"group_size": 64,
|
| 253 |
+
"bits": 8
|
| 254 |
+
},
|
| 255 |
+
"model.layers.7.mlp.gate": {
|
| 256 |
+
"group_size": 64,
|
| 257 |
+
"bits": 8
|
| 258 |
+
},
|
| 259 |
+
"model.layers.8.mlp.gate": {
|
| 260 |
+
"group_size": 64,
|
| 261 |
+
"bits": 8
|
| 262 |
+
},
|
| 263 |
+
"model.layers.9.mlp.gate": {
|
| 264 |
+
"group_size": 64,
|
| 265 |
+
"bits": 8
|
| 266 |
+
},
|
| 267 |
+
"model.layers.10.mlp.gate": {
|
| 268 |
+
"group_size": 64,
|
| 269 |
+
"bits": 8
|
| 270 |
+
},
|
| 271 |
+
"model.layers.11.mlp.gate": {
|
| 272 |
+
"group_size": 64,
|
| 273 |
+
"bits": 8
|
| 274 |
+
},
|
| 275 |
+
"model.layers.12.mlp.gate": {
|
| 276 |
+
"group_size": 64,
|
| 277 |
+
"bits": 8
|
| 278 |
+
},
|
| 279 |
+
"model.layers.13.mlp.gate": {
|
| 280 |
+
"group_size": 64,
|
| 281 |
+
"bits": 8
|
| 282 |
+
},
|
| 283 |
+
"model.layers.14.mlp.gate": {
|
| 284 |
+
"group_size": 64,
|
| 285 |
+
"bits": 8
|
| 286 |
+
},
|
| 287 |
+
"model.layers.15.mlp.gate": {
|
| 288 |
+
"group_size": 64,
|
| 289 |
+
"bits": 8
|
| 290 |
+
},
|
| 291 |
+
"model.layers.16.mlp.gate": {
|
| 292 |
+
"group_size": 64,
|
| 293 |
+
"bits": 8
|
| 294 |
+
},
|
| 295 |
+
"model.layers.17.mlp.gate": {
|
| 296 |
+
"group_size": 64,
|
| 297 |
+
"bits": 8
|
| 298 |
+
},
|
| 299 |
+
"model.layers.18.mlp.gate": {
|
| 300 |
+
"group_size": 64,
|
| 301 |
+
"bits": 8
|
| 302 |
+
},
|
| 303 |
+
"model.layers.19.mlp.gate": {
|
| 304 |
+
"group_size": 64,
|
| 305 |
+
"bits": 8
|
| 306 |
+
},
|
| 307 |
+
"model.layers.20.mlp.gate": {
|
| 308 |
+
"group_size": 64,
|
| 309 |
+
"bits": 8
|
| 310 |
+
},
|
| 311 |
+
"model.layers.21.mlp.gate": {
|
| 312 |
+
"group_size": 64,
|
| 313 |
+
"bits": 8
|
| 314 |
+
},
|
| 315 |
+
"model.layers.22.mlp.gate": {
|
| 316 |
+
"group_size": 64,
|
| 317 |
+
"bits": 8
|
| 318 |
+
},
|
| 319 |
+
"model.layers.23.mlp.gate": {
|
| 320 |
+
"group_size": 64,
|
| 321 |
+
"bits": 8
|
| 322 |
+
},
|
| 323 |
+
"model.layers.24.mlp.gate": {
|
| 324 |
+
"group_size": 64,
|
| 325 |
+
"bits": 8
|
| 326 |
+
},
|
| 327 |
+
"model.layers.25.mlp.gate": {
|
| 328 |
+
"group_size": 64,
|
| 329 |
+
"bits": 8
|
| 330 |
+
},
|
| 331 |
+
"model.layers.26.mlp.gate": {
|
| 332 |
+
"group_size": 64,
|
| 333 |
+
"bits": 8
|
| 334 |
+
},
|
| 335 |
+
"model.layers.27.mlp.gate": {
|
| 336 |
+
"group_size": 64,
|
| 337 |
+
"bits": 8
|
| 338 |
+
},
|
| 339 |
+
"model.layers.28.mlp.gate": {
|
| 340 |
+
"group_size": 64,
|
| 341 |
+
"bits": 8
|
| 342 |
+
},
|
| 343 |
+
"model.layers.29.mlp.gate": {
|
| 344 |
+
"group_size": 64,
|
| 345 |
+
"bits": 8
|
| 346 |
+
},
|
| 347 |
+
"model.layers.30.mlp.gate": {
|
| 348 |
+
"group_size": 64,
|
| 349 |
+
"bits": 8
|
| 350 |
+
},
|
| 351 |
+
"model.layers.31.mlp.gate": {
|
| 352 |
+
"group_size": 64,
|
| 353 |
+
"bits": 8
|
| 354 |
+
},
|
| 355 |
+
"model.layers.32.mlp.gate": {
|
| 356 |
+
"group_size": 64,
|
| 357 |
+
"bits": 8
|
| 358 |
+
},
|
| 359 |
+
"model.layers.33.mlp.gate": {
|
| 360 |
+
"group_size": 64,
|
| 361 |
+
"bits": 8
|
| 362 |
+
},
|
| 363 |
+
"model.layers.34.mlp.gate": {
|
| 364 |
+
"group_size": 64,
|
| 365 |
+
"bits": 8
|
| 366 |
+
},
|
| 367 |
+
"model.layers.35.mlp.gate": {
|
| 368 |
+
"group_size": 64,
|
| 369 |
+
"bits": 8
|
| 370 |
+
},
|
| 371 |
+
"model.layers.36.mlp.gate": {
|
| 372 |
+
"group_size": 64,
|
| 373 |
+
"bits": 8
|
| 374 |
+
},
|
| 375 |
+
"model.layers.37.mlp.gate": {
|
| 376 |
+
"group_size": 64,
|
| 377 |
+
"bits": 8
|
| 378 |
+
},
|
| 379 |
+
"model.layers.38.mlp.gate": {
|
| 380 |
+
"group_size": 64,
|
| 381 |
+
"bits": 8
|
| 382 |
+
},
|
| 383 |
+
"model.layers.39.mlp.gate": {
|
| 384 |
+
"group_size": 64,
|
| 385 |
+
"bits": 8
|
| 386 |
+
},
|
| 387 |
+
"model.layers.40.mlp.gate": {
|
| 388 |
+
"group_size": 64,
|
| 389 |
+
"bits": 8
|
| 390 |
+
},
|
| 391 |
+
"model.layers.41.mlp.gate": {
|
| 392 |
+
"group_size": 64,
|
| 393 |
+
"bits": 8
|
| 394 |
+
},
|
| 395 |
+
"model.layers.42.mlp.gate": {
|
| 396 |
+
"group_size": 64,
|
| 397 |
+
"bits": 8
|
| 398 |
+
},
|
| 399 |
+
"model.layers.43.mlp.gate": {
|
| 400 |
+
"group_size": 64,
|
| 401 |
+
"bits": 8
|
| 402 |
+
},
|
| 403 |
+
"model.layers.44.mlp.gate": {
|
| 404 |
+
"group_size": 64,
|
| 405 |
+
"bits": 8
|
| 406 |
+
},
|
| 407 |
+
"model.layers.45.mlp.gate": {
|
| 408 |
+
"group_size": 64,
|
| 409 |
+
"bits": 8
|
| 410 |
+
},
|
| 411 |
+
"model.layers.46.mlp.gate": {
|
| 412 |
+
"group_size": 64,
|
| 413 |
+
"bits": 8
|
| 414 |
+
},
|
| 415 |
+
"model.layers.47.mlp.gate": {
|
| 416 |
+
"group_size": 64,
|
| 417 |
+
"bits": 8
|
| 418 |
+
}
|
| 419 |
+
},
|
| 420 |
+
"rms_norm_eps": 1e-06,
|
| 421 |
+
"rope_scaling": null,
|
| 422 |
+
"rope_theta": 10000000,
|
| 423 |
+
"router_aux_loss_coef": 0.0,
|
| 424 |
+
"shared_expert_intermediate_size": 0,
|
| 425 |
+
"sliding_window": null,
|
| 426 |
+
"tie_word_embeddings": false,
|
| 427 |
+
"torch_dtype": "bfloat16",
|
| 428 |
+
"transformers_version": "4.52.3",
|
| 429 |
+
"use_cache": true,
|
| 430 |
+
"use_qk_norm": true,
|
| 431 |
+
"use_sliding_window": false,
|
| 432 |
+
"vocab_size": 151936
|
| 433 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"top_k": 20
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61307530f3b5cac1d5a2914d4a5f880e77e6917d343598efd73e43362140f60a
|
| 3 |
+
size 5357246273
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef623a7c32b99cc807c7a390b557813e28e9f9041a6f39564b347a11cdc3297d
|
| 3 |
+
size 5298895040
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c4743f51b209f0f676520df465a09b82b9d301e26b1e2ccc3f4c599f324d738
|
| 3 |
+
size 5298895020
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17da5c3603cb0c6b904297db6a712c12022a3a6f2a2230d910e4c2c952bfbce2
|
| 3 |
+
size 272265757
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1021 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16227184640,
|
| 4 |
+
"total_parameters": 30532122624
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.scales": "model-00004-of-00004.safetensors",
|
| 8 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 9 |
+
"model.embed_tokens.scales": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.1.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.layers.1.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.layers.1.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 39 |
+
"model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 41 |
+
"model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 43 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 45 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 47 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 53 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"model.layers.10.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 55 |
+
"model.layers.10.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 56 |
+
"model.layers.10.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 57 |
+
"model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 58 |
+
"model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 59 |
+
"model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 60 |
+
"model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 61 |
+
"model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 62 |
+
"model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 63 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 64 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 65 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 66 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 67 |
+
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 68 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 72 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 73 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 74 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 75 |
+
"model.layers.11.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 76 |
+
"model.layers.11.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 77 |
+
"model.layers.11.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 78 |
+
"model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 79 |
+
"model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 80 |
+
"model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 81 |
+
"model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 82 |
+
"model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 83 |
+
"model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 84 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 85 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 86 |
+
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 87 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 88 |
+
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 89 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 90 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 91 |
+
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 92 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 93 |
+
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 94 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 95 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 96 |
+
"model.layers.12.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 97 |
+
"model.layers.12.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 98 |
+
"model.layers.12.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 99 |
+
"model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 100 |
+
"model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 101 |
+
"model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 102 |
+
"model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 103 |
+
"model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 104 |
+
"model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 105 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 106 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 107 |
+
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 108 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 109 |
+
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 110 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 111 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 112 |
+
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 113 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 114 |
+
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 115 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 116 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.13.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.13.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.13.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 126 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 127 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 128 |
+
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 129 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 130 |
+
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 131 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 132 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 133 |
+
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 134 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 135 |
+
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 136 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 137 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 138 |
+
"model.layers.14.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 139 |
+
"model.layers.14.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 140 |
+
"model.layers.14.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.15.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.15.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.15.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 166 |
+
"model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 167 |
+
"model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 168 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 169 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 170 |
+
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 171 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 172 |
+
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 173 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 175 |
+
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 176 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 177 |
+
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 178 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 179 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.16.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.16.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.16.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 186 |
+
"model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 187 |
+
"model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 188 |
+
"model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 189 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 190 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 191 |
+
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 192 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 193 |
+
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 194 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 195 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 196 |
+
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 197 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 198 |
+
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 199 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 200 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 201 |
+
"model.layers.17.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 202 |
+
"model.layers.17.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 203 |
+
"model.layers.17.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 204 |
+
"model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 205 |
+
"model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 206 |
+
"model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 207 |
+
"model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 208 |
+
"model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 209 |
+
"model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 210 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 211 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 212 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 213 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 214 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 215 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 216 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 217 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 218 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 219 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 220 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 221 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 222 |
+
"model.layers.18.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 223 |
+
"model.layers.18.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 224 |
+
"model.layers.18.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 225 |
+
"model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 226 |
+
"model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 227 |
+
"model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 228 |
+
"model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 229 |
+
"model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 230 |
+
"model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 231 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 232 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 233 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 234 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 235 |
+
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 236 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 237 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 238 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 239 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 240 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 241 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 242 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 243 |
+
"model.layers.19.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 244 |
+
"model.layers.19.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 245 |
+
"model.layers.19.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 246 |
+
"model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 247 |
+
"model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 248 |
+
"model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 249 |
+
"model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 250 |
+
"model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 251 |
+
"model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 253 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 254 |
+
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 255 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 256 |
+
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 257 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 258 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 259 |
+
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 260 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 261 |
+
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 262 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 263 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.2.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.2.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.2.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"model.layers.20.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 286 |
+
"model.layers.20.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 287 |
+
"model.layers.20.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 302 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 304 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"model.layers.21.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 307 |
+
"model.layers.21.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 308 |
+
"model.layers.21.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 312 |
+
"model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.layers.22.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 328 |
+
"model.layers.22.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 329 |
+
"model.layers.22.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 346 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 347 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 348 |
+
"model.layers.23.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 349 |
+
"model.layers.23.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 350 |
+
"model.layers.23.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 351 |
+
"model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 352 |
+
"model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 354 |
+
"model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 356 |
+
"model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 360 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 365 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 367 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.layers.24.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.layers.24.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.layers.24.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.layers.25.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.layers.25.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.layers.25.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 407 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.layers.26.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.layers.26.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 413 |
+
"model.layers.26.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 414 |
+
"model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 415 |
+
"model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 419 |
+
"model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 421 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 423 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 424 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 425 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 426 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 428 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 430 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.layers.27.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.layers.27.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 434 |
+
"model.layers.27.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 435 |
+
"model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 436 |
+
"model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 437 |
+
"model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 438 |
+
"model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 439 |
+
"model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 440 |
+
"model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 441 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 442 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 443 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 444 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 445 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 446 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 447 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 448 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 449 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 450 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 451 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 452 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 453 |
+
"model.layers.28.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 454 |
+
"model.layers.28.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 455 |
+
"model.layers.28.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 456 |
+
"model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 457 |
+
"model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 458 |
+
"model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 459 |
+
"model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 460 |
+
"model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 461 |
+
"model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 462 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 463 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 464 |
+
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 465 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 466 |
+
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 467 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 468 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 469 |
+
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 470 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 471 |
+
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 472 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 473 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 474 |
+
"model.layers.29.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 475 |
+
"model.layers.29.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 476 |
+
"model.layers.29.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 477 |
+
"model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 478 |
+
"model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 479 |
+
"model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 480 |
+
"model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 481 |
+
"model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 482 |
+
"model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 483 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 484 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 485 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 486 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 487 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 488 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 489 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 490 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 491 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 492 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 493 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 494 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.layers.3.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.layers.3.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.layers.3.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 516 |
+
"model.layers.30.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 517 |
+
"model.layers.30.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 518 |
+
"model.layers.30.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 519 |
+
"model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 520 |
+
"model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 521 |
+
"model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 522 |
+
"model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 523 |
+
"model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 524 |
+
"model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 525 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 526 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 527 |
+
"model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 528 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 529 |
+
"model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 530 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 531 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 532 |
+
"model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 533 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 534 |
+
"model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 535 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 536 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 537 |
+
"model.layers.31.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 538 |
+
"model.layers.31.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 539 |
+
"model.layers.31.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 540 |
+
"model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 541 |
+
"model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 542 |
+
"model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 543 |
+
"model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 544 |
+
"model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 545 |
+
"model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 546 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 547 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 548 |
+
"model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
|
| 549 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 550 |
+
"model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
|
| 551 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 552 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 553 |
+
"model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
|
| 554 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 555 |
+
"model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
|
| 556 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 557 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 558 |
+
"model.layers.32.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 559 |
+
"model.layers.32.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 560 |
+
"model.layers.32.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 561 |
+
"model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 562 |
+
"model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 563 |
+
"model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 564 |
+
"model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 565 |
+
"model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 566 |
+
"model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 567 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 568 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 569 |
+
"model.layers.32.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 570 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 571 |
+
"model.layers.32.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 572 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 573 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 574 |
+
"model.layers.32.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 575 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 576 |
+
"model.layers.32.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 577 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 578 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 579 |
+
"model.layers.33.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 580 |
+
"model.layers.33.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 581 |
+
"model.layers.33.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 582 |
+
"model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 583 |
+
"model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 584 |
+
"model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 585 |
+
"model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 586 |
+
"model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 587 |
+
"model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 588 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 589 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 590 |
+
"model.layers.33.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 591 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 592 |
+
"model.layers.33.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 593 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 594 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 595 |
+
"model.layers.33.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 596 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 597 |
+
"model.layers.33.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 598 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 599 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 600 |
+
"model.layers.34.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 601 |
+
"model.layers.34.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 602 |
+
"model.layers.34.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 603 |
+
"model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 604 |
+
"model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 605 |
+
"model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 606 |
+
"model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 607 |
+
"model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 608 |
+
"model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 609 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 610 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 611 |
+
"model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 612 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 613 |
+
"model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 614 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 615 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 616 |
+
"model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 617 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 618 |
+
"model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 619 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 620 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 621 |
+
"model.layers.35.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 622 |
+
"model.layers.35.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 623 |
+
"model.layers.35.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 624 |
+
"model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 625 |
+
"model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 626 |
+
"model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 627 |
+
"model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 628 |
+
"model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 629 |
+
"model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 630 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 631 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 632 |
+
"model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 633 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 634 |
+
"model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 635 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 636 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 637 |
+
"model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 638 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 639 |
+
"model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 640 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 641 |
+
"model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 642 |
+
"model.layers.36.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 643 |
+
"model.layers.36.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 644 |
+
"model.layers.36.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 645 |
+
"model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 646 |
+
"model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 647 |
+
"model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 648 |
+
"model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 649 |
+
"model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 650 |
+
"model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 651 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 652 |
+
"model.layers.36.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 653 |
+
"model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 654 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 655 |
+
"model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 656 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 657 |
+
"model.layers.36.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 658 |
+
"model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 659 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 660 |
+
"model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 662 |
+
"model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 663 |
+
"model.layers.37.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 664 |
+
"model.layers.37.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 665 |
+
"model.layers.37.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 666 |
+
"model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 667 |
+
"model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 669 |
+
"model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 670 |
+
"model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 672 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 674 |
+
"model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 675 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 676 |
+
"model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 677 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 678 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 680 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
+
"model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.layers.38.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 685 |
+
"model.layers.38.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 686 |
+
"model.layers.38.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 687 |
+
"model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
+
"model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 690 |
+
"model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 694 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 696 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 697 |
+
"model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 698 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 699 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 702 |
+
"model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 703 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 704 |
+
"model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 705 |
+
"model.layers.39.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 706 |
+
"model.layers.39.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 707 |
+
"model.layers.39.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 708 |
+
"model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 709 |
+
"model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 710 |
+
"model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 711 |
+
"model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 713 |
+
"model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 714 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"model.layers.39.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 716 |
+
"model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 717 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 718 |
+
"model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 719 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 720 |
+
"model.layers.39.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 721 |
+
"model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 722 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 723 |
+
"model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 725 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.layers.4.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.layers.4.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.layers.4.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 747 |
+
"model.layers.40.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 748 |
+
"model.layers.40.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 749 |
+
"model.layers.40.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 750 |
+
"model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 751 |
+
"model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 752 |
+
"model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 753 |
+
"model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 754 |
+
"model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 755 |
+
"model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 756 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 757 |
+
"model.layers.40.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 758 |
+
"model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 759 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 760 |
+
"model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 761 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 762 |
+
"model.layers.40.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 763 |
+
"model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 764 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
+
"model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 766 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 767 |
+
"model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 768 |
+
"model.layers.41.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 769 |
+
"model.layers.41.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 770 |
+
"model.layers.41.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 771 |
+
"model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 772 |
+
"model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 773 |
+
"model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 774 |
+
"model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 775 |
+
"model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 776 |
+
"model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 777 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 778 |
+
"model.layers.41.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 779 |
+
"model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 780 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 781 |
+
"model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 782 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 783 |
+
"model.layers.41.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 784 |
+
"model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 785 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 786 |
+
"model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 787 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 788 |
+
"model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 789 |
+
"model.layers.42.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 790 |
+
"model.layers.42.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 791 |
+
"model.layers.42.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 792 |
+
"model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 793 |
+
"model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 794 |
+
"model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 795 |
+
"model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 796 |
+
"model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 797 |
+
"model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 798 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 799 |
+
"model.layers.42.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 800 |
+
"model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 801 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 802 |
+
"model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 803 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 804 |
+
"model.layers.42.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 805 |
+
"model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 806 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 807 |
+
"model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 808 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 809 |
+
"model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 810 |
+
"model.layers.43.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 811 |
+
"model.layers.43.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 812 |
+
"model.layers.43.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 813 |
+
"model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 814 |
+
"model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 815 |
+
"model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 816 |
+
"model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 817 |
+
"model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 818 |
+
"model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 819 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 820 |
+
"model.layers.43.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 821 |
+
"model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 822 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 823 |
+
"model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 824 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 825 |
+
"model.layers.43.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 826 |
+
"model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 827 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 828 |
+
"model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 829 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 830 |
+
"model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 831 |
+
"model.layers.44.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 832 |
+
"model.layers.44.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 833 |
+
"model.layers.44.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 834 |
+
"model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 835 |
+
"model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 836 |
+
"model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 837 |
+
"model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 838 |
+
"model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 839 |
+
"model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 840 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 841 |
+
"model.layers.44.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 842 |
+
"model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 843 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 844 |
+
"model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 845 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 846 |
+
"model.layers.44.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 847 |
+
"model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 848 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 849 |
+
"model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 850 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 851 |
+
"model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 852 |
+
"model.layers.45.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 853 |
+
"model.layers.45.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 854 |
+
"model.layers.45.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 855 |
+
"model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 856 |
+
"model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 857 |
+
"model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 858 |
+
"model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 859 |
+
"model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 860 |
+
"model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 861 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 862 |
+
"model.layers.45.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 863 |
+
"model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 864 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 865 |
+
"model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 866 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 867 |
+
"model.layers.45.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 868 |
+
"model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 869 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 870 |
+
"model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 871 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 872 |
+
"model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 873 |
+
"model.layers.46.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 874 |
+
"model.layers.46.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 875 |
+
"model.layers.46.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 876 |
+
"model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 877 |
+
"model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 878 |
+
"model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 879 |
+
"model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 880 |
+
"model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 881 |
+
"model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 882 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 883 |
+
"model.layers.46.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 884 |
+
"model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 885 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 886 |
+
"model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 887 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 888 |
+
"model.layers.46.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 889 |
+
"model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 890 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 891 |
+
"model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 892 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 893 |
+
"model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 894 |
+
"model.layers.47.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 895 |
+
"model.layers.47.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 896 |
+
"model.layers.47.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 897 |
+
"model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 898 |
+
"model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 899 |
+
"model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 900 |
+
"model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 901 |
+
"model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 902 |
+
"model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 903 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 904 |
+
"model.layers.47.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 905 |
+
"model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
|
| 906 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 907 |
+
"model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
|
| 908 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 909 |
+
"model.layers.47.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 910 |
+
"model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
|
| 911 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 912 |
+
"model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
|
| 913 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 914 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 915 |
+
"model.layers.5.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 916 |
+
"model.layers.5.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 917 |
+
"model.layers.5.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 918 |
+
"model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 919 |
+
"model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 920 |
+
"model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 921 |
+
"model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 922 |
+
"model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 923 |
+
"model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 924 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 925 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 926 |
+
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 927 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 928 |
+
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 929 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 930 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 931 |
+
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 932 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 933 |
+
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 934 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 935 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 936 |
+
"model.layers.6.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 937 |
+
"model.layers.6.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 938 |
+
"model.layers.6.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 939 |
+
"model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 940 |
+
"model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 941 |
+
"model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 942 |
+
"model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 943 |
+
"model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 944 |
+
"model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 945 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 946 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 947 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 948 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 949 |
+
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 950 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 951 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 952 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 953 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 954 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 955 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 956 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 957 |
+
"model.layers.7.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 958 |
+
"model.layers.7.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 959 |
+
"model.layers.7.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 960 |
+
"model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 961 |
+
"model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 962 |
+
"model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 963 |
+
"model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 964 |
+
"model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 965 |
+
"model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 966 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 967 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 968 |
+
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 969 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 970 |
+
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 971 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 972 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 973 |
+
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 974 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 975 |
+
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 976 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 977 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 978 |
+
"model.layers.8.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 979 |
+
"model.layers.8.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 980 |
+
"model.layers.8.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 981 |
+
"model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 982 |
+
"model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 983 |
+
"model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 984 |
+
"model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 985 |
+
"model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 986 |
+
"model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 987 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 988 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 989 |
+
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 990 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 991 |
+
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 992 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 993 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 994 |
+
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 995 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 996 |
+
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 997 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 998 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 999 |
+
"model.layers.9.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 1000 |
+
"model.layers.9.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 1001 |
+
"model.layers.9.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 1002 |
+
"model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
|
| 1003 |
+
"model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 1004 |
+
"model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 1005 |
+
"model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 1006 |
+
"model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 1007 |
+
"model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 1008 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 1009 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 1010 |
+
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
|
| 1011 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 1012 |
+
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
|
| 1013 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 1014 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 1015 |
+
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
|
| 1016 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 1017 |
+
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 1018 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 1019 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 1020 |
+
}
|
| 1021 |
+
}
|
qwen3coder_tool_parser.py
ADDED
|
@@ -0,0 +1,689 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 2 |
+
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
| 3 |
+
import ast
|
| 4 |
+
import json
|
| 5 |
+
import uuid
|
| 6 |
+
from collections.abc import Sequence
|
| 7 |
+
from typing import Any, List, Optional, Union
|
| 8 |
+
|
| 9 |
+
import regex as re
|
| 10 |
+
|
| 11 |
+
from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
|
| 12 |
+
ChatCompletionToolsParam,
|
| 13 |
+
DeltaFunctionCall, DeltaMessage,
|
| 14 |
+
DeltaToolCall,
|
| 15 |
+
ExtractedToolCallInformation,
|
| 16 |
+
FunctionCall, ToolCall)
|
| 17 |
+
from vllm.entrypoints.openai.tool_parsers.abstract_tool_parser import (
|
| 18 |
+
ToolParser, ToolParserManager)
|
| 19 |
+
from vllm.logger import init_logger
|
| 20 |
+
from vllm.transformers_utils.tokenizer import AnyTokenizer
|
| 21 |
+
|
| 22 |
+
logger = init_logger(__name__)
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
@ToolParserManager.register_module("qwen3_coder")
|
| 26 |
+
class Qwen3CoderToolParser(ToolParser):
|
| 27 |
+
|
| 28 |
+
def __init__(self, tokenizer: AnyTokenizer):
|
| 29 |
+
super().__init__(tokenizer)
|
| 30 |
+
|
| 31 |
+
self.current_tool_name_sent: bool = False
|
| 32 |
+
self.prev_tool_call_arr: list[dict] = []
|
| 33 |
+
self.current_tool_id: int = -1
|
| 34 |
+
self.streamed_args_for_tool: list[str] = []
|
| 35 |
+
|
| 36 |
+
# Sentinel tokens for streaming mode
|
| 37 |
+
self.tool_call_start_token: str = "<tool_call>"
|
| 38 |
+
self.tool_call_end_token: str = "</tool_call>"
|
| 39 |
+
self.tool_call_prefix: str = "<function="
|
| 40 |
+
self.function_end_token: str = "</function>"
|
| 41 |
+
self.parameter_prefix: str = "<parameter="
|
| 42 |
+
self.parameter_end_token: str = "</parameter>"
|
| 43 |
+
self.is_tool_call_started: bool = False
|
| 44 |
+
self.failed_count: int = 0
|
| 45 |
+
|
| 46 |
+
# Enhanced streaming state - reset for each new message
|
| 47 |
+
self._reset_streaming_state()
|
| 48 |
+
|
| 49 |
+
# Regex patterns
|
| 50 |
+
self.tool_call_complete_regex = re.compile(
|
| 51 |
+
r"<tool_call>(.*?)</tool_call>", re.DOTALL)
|
| 52 |
+
self.tool_call_regex = re.compile(
|
| 53 |
+
r"<tool_call>(.*?)</tool_call>|<tool_call>(.*?)$", re.DOTALL)
|
| 54 |
+
self.tool_call_function_regex = re.compile(
|
| 55 |
+
r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL)
|
| 56 |
+
self.tool_call_parameter_regex = re.compile(
|
| 57 |
+
r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
|
| 58 |
+
re.DOTALL)
|
| 59 |
+
|
| 60 |
+
if not self.model_tokenizer:
|
| 61 |
+
raise ValueError(
|
| 62 |
+
"The model tokenizer must be passed to the ToolParser "
|
| 63 |
+
"constructor during construction.")
|
| 64 |
+
|
| 65 |
+
self.tool_call_start_token_id = self.vocab.get(
|
| 66 |
+
self.tool_call_start_token)
|
| 67 |
+
self.tool_call_end_token_id = self.vocab.get(self.tool_call_end_token)
|
| 68 |
+
|
| 69 |
+
if self.tool_call_start_token_id is None or self.tool_call_end_token_id is None:
|
| 70 |
+
raise RuntimeError(
|
| 71 |
+
"Qwen3 XML Tool parser could not locate tool call start/end "
|
| 72 |
+
"tokens in the tokenizer!")
|
| 73 |
+
|
| 74 |
+
logger.info(
|
| 75 |
+
f"vLLM Successfully import tool parser {self.__class__.__name__} !"
|
| 76 |
+
)
|
| 77 |
+
|
| 78 |
+
def _generate_tool_call_id(self) -> str:
|
| 79 |
+
"""Generate a unique tool call ID."""
|
| 80 |
+
return f"call_{uuid.uuid4().hex[:24]}"
|
| 81 |
+
|
| 82 |
+
def _reset_streaming_state(self):
|
| 83 |
+
"""Reset all streaming state."""
|
| 84 |
+
self.current_tool_index = 0
|
| 85 |
+
self.is_tool_call_started = False
|
| 86 |
+
self.header_sent = False
|
| 87 |
+
self.current_tool_id = None
|
| 88 |
+
self.current_function_name = None
|
| 89 |
+
self.current_param_name = None
|
| 90 |
+
self.current_param_value = ""
|
| 91 |
+
self.param_count = 0
|
| 92 |
+
self.in_param = False
|
| 93 |
+
self.in_function = False
|
| 94 |
+
self.accumulated_text = ""
|
| 95 |
+
self.json_started = False
|
| 96 |
+
self.json_closed = False
|
| 97 |
+
# Store accumulated parameters for type conversion
|
| 98 |
+
self.accumulated_params = {}
|
| 99 |
+
self.streaming_request = None
|
| 100 |
+
|
| 101 |
+
def _get_arguments_config(
|
| 102 |
+
self, func_name: str,
|
| 103 |
+
tools: Optional[list[ChatCompletionToolsParam]]) -> dict:
|
| 104 |
+
"""Extract argument configuration for a function."""
|
| 105 |
+
if tools is None:
|
| 106 |
+
return {}
|
| 107 |
+
for config in tools:
|
| 108 |
+
if not hasattr(config, "type") or not (hasattr(
|
| 109 |
+
config, "function") and hasattr(config.function, "name")):
|
| 110 |
+
continue
|
| 111 |
+
if config.type == "function" and config.function.name == func_name:
|
| 112 |
+
if not hasattr(config.function, "parameters"):
|
| 113 |
+
return {}
|
| 114 |
+
params = config.function.parameters
|
| 115 |
+
if isinstance(params, dict) and "properties" in params:
|
| 116 |
+
return params["properties"]
|
| 117 |
+
elif isinstance(params, dict):
|
| 118 |
+
return params
|
| 119 |
+
else:
|
| 120 |
+
return {}
|
| 121 |
+
logger.warning(f"Tool '{func_name}' is not defined in the tools list.")
|
| 122 |
+
return {}
|
| 123 |
+
|
| 124 |
+
def _convert_param_value(self, param_value: str, param_name: str,
|
| 125 |
+
param_config: dict, func_name: str) -> Any:
|
| 126 |
+
"""Convert parameter value based on its type in the schema."""
|
| 127 |
+
# Handle null value for any type
|
| 128 |
+
if param_value.lower() == "null":
|
| 129 |
+
return None
|
| 130 |
+
|
| 131 |
+
if param_name not in param_config:
|
| 132 |
+
if param_config != {}:
|
| 133 |
+
logger.warning(
|
| 134 |
+
f"Parsed parameter '{param_name}' is not defined in the tool "
|
| 135 |
+
f"parameters for tool '{func_name}', directly returning the string value."
|
| 136 |
+
)
|
| 137 |
+
return param_value
|
| 138 |
+
|
| 139 |
+
if isinstance(param_config[param_name],
|
| 140 |
+
dict) and "type" in param_config[param_name]:
|
| 141 |
+
param_type = str(param_config[param_name]["type"]).strip().lower()
|
| 142 |
+
else:
|
| 143 |
+
param_type = "string"
|
| 144 |
+
if param_type in ["string", "str", "text", "varchar", "char", "enum"]:
|
| 145 |
+
return param_value
|
| 146 |
+
elif param_type.startswith("int") or param_type.startswith(
|
| 147 |
+
"uint") or param_type.startswith(
|
| 148 |
+
"long") or param_type.startswith(
|
| 149 |
+
"short") or param_type.startswith("unsigned"):
|
| 150 |
+
try:
|
| 151 |
+
param_value = int(param_value)
|
| 152 |
+
except:
|
| 153 |
+
logger.warning(
|
| 154 |
+
f"Parsed value '{param_value}' of parameter '{param_name}' is not an integer in tool "
|
| 155 |
+
f"'{func_name}', degenerating to string.")
|
| 156 |
+
return param_value
|
| 157 |
+
elif param_type.startswith("num") or param_type.startswith("float"):
|
| 158 |
+
try:
|
| 159 |
+
float_param_value = float(param_value)
|
| 160 |
+
param_value = float_param_value if float_param_value - int(
|
| 161 |
+
float_param_value) != 0 else int(float_param_value)
|
| 162 |
+
except:
|
| 163 |
+
logger.warning(
|
| 164 |
+
f"Parsed value '{param_value}' of parameter '{param_name}' is not a float in tool "
|
| 165 |
+
f"'{func_name}', degenerating to string.")
|
| 166 |
+
return param_value
|
| 167 |
+
elif param_type in ["boolean", "bool", "binary"]:
|
| 168 |
+
param_value = param_value.lower()
|
| 169 |
+
if param_value not in ["true", "false"]:
|
| 170 |
+
logger.warning(
|
| 171 |
+
f"Parsed value '{param_value}' of parameter '{param_name}' is not a boolean (`true` of `false`) in tool '{func_name}', degenerating to false."
|
| 172 |
+
)
|
| 173 |
+
return param_value == "true"
|
| 174 |
+
else:
|
| 175 |
+
if param_type in ["object", "array", "arr"
|
| 176 |
+
] or param_type.startswith(
|
| 177 |
+
"dict") or param_type.startswith("list"):
|
| 178 |
+
try:
|
| 179 |
+
param_value = json.loads(param_value)
|
| 180 |
+
return param_value
|
| 181 |
+
except:
|
| 182 |
+
logger.warning(
|
| 183 |
+
f"Parsed value '{param_value}' of parameter '{param_name}' cannot be parsed with json.loads in tool "
|
| 184 |
+
f"'{func_name}', will try other methods to parse it.")
|
| 185 |
+
try:
|
| 186 |
+
param_value = ast.literal_eval(param_value) # safer
|
| 187 |
+
except:
|
| 188 |
+
logger.warning(
|
| 189 |
+
f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `ast.literal_eval()` in tool '{func_name}', degenerating to string."
|
| 190 |
+
)
|
| 191 |
+
return param_value
|
| 192 |
+
|
| 193 |
+
def _parse_xml_function_call(
|
| 194 |
+
self, function_call_str: str,
|
| 195 |
+
tools: Optional[list[ChatCompletionToolsParam]]
|
| 196 |
+
) -> Optional[ToolCall]:
|
| 197 |
+
|
| 198 |
+
# Extract function name
|
| 199 |
+
end_index = function_call_str.index(">")
|
| 200 |
+
function_name = function_call_str[:end_index]
|
| 201 |
+
param_config = self._get_arguments_config(function_name, tools)
|
| 202 |
+
parameters = function_call_str[end_index + 1:]
|
| 203 |
+
param_dict = {}
|
| 204 |
+
for match_text in self.tool_call_parameter_regex.findall(parameters):
|
| 205 |
+
idx = match_text.index(">")
|
| 206 |
+
param_name = match_text[:idx]
|
| 207 |
+
param_value = str(match_text[idx + 1:])
|
| 208 |
+
# Remove prefix and trailing \n
|
| 209 |
+
if param_value.startswith("\n"):
|
| 210 |
+
param_value = param_value[1:]
|
| 211 |
+
if param_value.endswith("\n"):
|
| 212 |
+
param_value = param_value[:-1]
|
| 213 |
+
|
| 214 |
+
param_dict[param_name] = self._convert_param_value(
|
| 215 |
+
param_value, param_name, param_config, function_name)
|
| 216 |
+
return ToolCall(
|
| 217 |
+
type="function",
|
| 218 |
+
function=FunctionCall(name=function_name,
|
| 219 |
+
arguments=json.dumps(param_dict,
|
| 220 |
+
ensure_ascii=False)),
|
| 221 |
+
)
|
| 222 |
+
|
| 223 |
+
def _get_function_calls(self, model_output: str) -> List[str]:
|
| 224 |
+
# Find all tool calls
|
| 225 |
+
matched_ranges = self.tool_call_regex.findall(model_output)
|
| 226 |
+
raw_tool_calls = [
|
| 227 |
+
match[0] if match[0] else match[1] for match in matched_ranges
|
| 228 |
+
]
|
| 229 |
+
|
| 230 |
+
# Back-off strategy if no tool_call tags found
|
| 231 |
+
if len(raw_tool_calls) == 0:
|
| 232 |
+
raw_tool_calls = [model_output]
|
| 233 |
+
|
| 234 |
+
raw_function_calls = []
|
| 235 |
+
for tool_call in raw_tool_calls:
|
| 236 |
+
raw_function_calls.extend(
|
| 237 |
+
self.tool_call_function_regex.findall(tool_call))
|
| 238 |
+
|
| 239 |
+
function_calls = [
|
| 240 |
+
match[0] if match[0] else match[1] for match in raw_function_calls
|
| 241 |
+
]
|
| 242 |
+
return function_calls
|
| 243 |
+
|
| 244 |
+
def extract_tool_calls(
|
| 245 |
+
self,
|
| 246 |
+
model_output: str,
|
| 247 |
+
request: ChatCompletionRequest,
|
| 248 |
+
) -> ExtractedToolCallInformation:
|
| 249 |
+
# Quick check to avoid unnecessary processing
|
| 250 |
+
if self.tool_call_prefix not in model_output:
|
| 251 |
+
return ExtractedToolCallInformation(tools_called=False,
|
| 252 |
+
tool_calls=[],
|
| 253 |
+
content=model_output)
|
| 254 |
+
|
| 255 |
+
try:
|
| 256 |
+
function_calls = self._get_function_calls(model_output)
|
| 257 |
+
if len(function_calls) == 0:
|
| 258 |
+
return ExtractedToolCallInformation(tools_called=False,
|
| 259 |
+
tool_calls=[],
|
| 260 |
+
content=model_output)
|
| 261 |
+
|
| 262 |
+
tool_calls = [
|
| 263 |
+
self._parse_xml_function_call(function_call_str, request.tools)
|
| 264 |
+
for function_call_str in function_calls
|
| 265 |
+
]
|
| 266 |
+
|
| 267 |
+
# Populate prev_tool_call_arr for serving layer to set finish_reason
|
| 268 |
+
self.prev_tool_call_arr.clear() # Clear previous calls
|
| 269 |
+
for tool_call in tool_calls:
|
| 270 |
+
if tool_call:
|
| 271 |
+
self.prev_tool_call_arr.append({
|
| 272 |
+
"name":
|
| 273 |
+
tool_call.function.name,
|
| 274 |
+
"arguments":
|
| 275 |
+
tool_call.function.arguments,
|
| 276 |
+
})
|
| 277 |
+
|
| 278 |
+
# Extract content before tool calls
|
| 279 |
+
content_index = model_output.find(self.tool_call_start_token)
|
| 280 |
+
content_index = content_index if content_index >= 0 else model_output.find(
|
| 281 |
+
self.tool_call_prefix)
|
| 282 |
+
content = model_output[:content_index] # .rstrip()
|
| 283 |
+
|
| 284 |
+
return ExtractedToolCallInformation(
|
| 285 |
+
tools_called=(len(tool_calls) > 0),
|
| 286 |
+
tool_calls=tool_calls,
|
| 287 |
+
content=content if content else None,
|
| 288 |
+
)
|
| 289 |
+
|
| 290 |
+
except Exception:
|
| 291 |
+
logger.exception("Error in extracting tool call from response.")
|
| 292 |
+
return ExtractedToolCallInformation(tools_called=False,
|
| 293 |
+
tool_calls=[],
|
| 294 |
+
content=model_output)
|
| 295 |
+
|
| 296 |
+
def extract_tool_calls_streaming(
|
| 297 |
+
self,
|
| 298 |
+
previous_text: str,
|
| 299 |
+
current_text: str,
|
| 300 |
+
delta_text: str,
|
| 301 |
+
previous_token_ids: Sequence[int],
|
| 302 |
+
current_token_ids: Sequence[int],
|
| 303 |
+
delta_token_ids: Sequence[int],
|
| 304 |
+
request: ChatCompletionRequest,
|
| 305 |
+
) -> Union[DeltaMessage, None]:
|
| 306 |
+
# Store request for type conversion
|
| 307 |
+
if not previous_text:
|
| 308 |
+
self._reset_streaming_state()
|
| 309 |
+
self.streaming_request = request
|
| 310 |
+
|
| 311 |
+
# If no delta text, return None unless it's an EOS token after tool calls
|
| 312 |
+
if not delta_text:
|
| 313 |
+
# Check if this is an EOS token after all tool calls are complete
|
| 314 |
+
# We check for tool calls in the text even if is_tool_call_started is False
|
| 315 |
+
# because it might have been reset after processing all tools
|
| 316 |
+
if delta_token_ids and self.tool_call_end_token_id not in delta_token_ids:
|
| 317 |
+
# Count complete tool calls
|
| 318 |
+
complete_calls = len(
|
| 319 |
+
self.tool_call_complete_regex.findall(current_text))
|
| 320 |
+
|
| 321 |
+
# If we have completed tool calls and populated prev_tool_call_arr
|
| 322 |
+
if complete_calls > 0 and len(self.prev_tool_call_arr) > 0:
|
| 323 |
+
# Check if all tool calls are closed
|
| 324 |
+
open_calls = current_text.count(
|
| 325 |
+
self.tool_call_start_token) - current_text.count(
|
| 326 |
+
self.tool_call_end_token)
|
| 327 |
+
if open_calls == 0:
|
| 328 |
+
# Return empty delta message to allow finish_reason processing
|
| 329 |
+
return DeltaMessage(content="")
|
| 330 |
+
elif not self.is_tool_call_started and current_text:
|
| 331 |
+
# This is a regular content response that's now complete
|
| 332 |
+
return DeltaMessage(content="")
|
| 333 |
+
return None
|
| 334 |
+
|
| 335 |
+
# Update accumulated text
|
| 336 |
+
self.accumulated_text = current_text
|
| 337 |
+
|
| 338 |
+
# Check if we need to advance to next tool
|
| 339 |
+
if self.json_closed and not self.in_function:
|
| 340 |
+
# Check if this tool call has ended
|
| 341 |
+
tool_ends = current_text.count(self.tool_call_end_token)
|
| 342 |
+
if tool_ends > self.current_tool_index:
|
| 343 |
+
# This tool has ended, advance to next
|
| 344 |
+
self.current_tool_index += 1
|
| 345 |
+
self.header_sent = False
|
| 346 |
+
self.param_count = 0
|
| 347 |
+
self.json_started = False
|
| 348 |
+
self.json_closed = False
|
| 349 |
+
self.accumulated_params = {}
|
| 350 |
+
|
| 351 |
+
# Check if there are more tool calls
|
| 352 |
+
tool_starts = current_text.count(self.tool_call_start_token)
|
| 353 |
+
if self.current_tool_index >= tool_starts:
|
| 354 |
+
# No more tool calls
|
| 355 |
+
self.is_tool_call_started = False
|
| 356 |
+
# Continue processing next tool
|
| 357 |
+
return None
|
| 358 |
+
|
| 359 |
+
# Handle normal content before tool calls
|
| 360 |
+
if not self.is_tool_call_started:
|
| 361 |
+
# Check if tool call is starting
|
| 362 |
+
if self.tool_call_start_token_id in delta_token_ids or self.tool_call_start_token in delta_text:
|
| 363 |
+
self.is_tool_call_started = True
|
| 364 |
+
# Return any content before the tool call
|
| 365 |
+
if self.tool_call_start_token in delta_text:
|
| 366 |
+
content_before = delta_text[:delta_text.index(
|
| 367 |
+
self.tool_call_start_token)]
|
| 368 |
+
if content_before:
|
| 369 |
+
return DeltaMessage(content=content_before)
|
| 370 |
+
return None
|
| 371 |
+
else:
|
| 372 |
+
# Check if we're between tool calls - skip whitespace
|
| 373 |
+
if current_text.rstrip().endswith(self.tool_call_end_token):
|
| 374 |
+
# We just ended a tool call, skip whitespace
|
| 375 |
+
if delta_text.strip() == "":
|
| 376 |
+
return None
|
| 377 |
+
# Normal content, no tool call
|
| 378 |
+
return DeltaMessage(content=delta_text)
|
| 379 |
+
|
| 380 |
+
# Check if we're between tool calls (waiting for next one)
|
| 381 |
+
# Count tool calls we've seen vs processed
|
| 382 |
+
tool_starts_count = current_text.count(self.tool_call_start_token)
|
| 383 |
+
if self.current_tool_index >= tool_starts_count:
|
| 384 |
+
# We're past all tool calls, shouldn't be here
|
| 385 |
+
return None
|
| 386 |
+
|
| 387 |
+
# We're in a tool call, find the current tool call portion
|
| 388 |
+
# Need to find the correct tool call based on current_tool_index
|
| 389 |
+
tool_starts = []
|
| 390 |
+
idx = 0
|
| 391 |
+
while True:
|
| 392 |
+
idx = current_text.find(self.tool_call_start_token, idx)
|
| 393 |
+
if idx == -1:
|
| 394 |
+
break
|
| 395 |
+
tool_starts.append(idx)
|
| 396 |
+
idx += len(self.tool_call_start_token)
|
| 397 |
+
|
| 398 |
+
if self.current_tool_index >= len(tool_starts):
|
| 399 |
+
# No more tool calls to process yet
|
| 400 |
+
return None
|
| 401 |
+
|
| 402 |
+
tool_start_idx = tool_starts[self.current_tool_index]
|
| 403 |
+
# Find where this tool call ends (or current position if not ended yet)
|
| 404 |
+
tool_end_idx = current_text.find(self.tool_call_end_token,
|
| 405 |
+
tool_start_idx)
|
| 406 |
+
if tool_end_idx == -1:
|
| 407 |
+
tool_text = current_text[tool_start_idx:]
|
| 408 |
+
else:
|
| 409 |
+
tool_text = current_text[tool_start_idx:tool_end_idx +
|
| 410 |
+
len(self.tool_call_end_token)]
|
| 411 |
+
|
| 412 |
+
# Looking for function header
|
| 413 |
+
if not self.header_sent:
|
| 414 |
+
if self.tool_call_prefix in tool_text:
|
| 415 |
+
func_start = tool_text.find(self.tool_call_prefix) + len(
|
| 416 |
+
self.tool_call_prefix)
|
| 417 |
+
func_end = tool_text.find(">", func_start)
|
| 418 |
+
|
| 419 |
+
if func_end != -1:
|
| 420 |
+
# Found complete function name
|
| 421 |
+
self.current_function_name = tool_text[func_start:func_end]
|
| 422 |
+
self.current_tool_id = self._generate_tool_call_id()
|
| 423 |
+
self.header_sent = True
|
| 424 |
+
self.in_function = True
|
| 425 |
+
|
| 426 |
+
# IMPORTANT: Add to prev_tool_call_arr immediately when we detect a tool call
|
| 427 |
+
# This ensures finish_reason="tool_calls" even if parsing isn't complete
|
| 428 |
+
already_added = any(
|
| 429 |
+
tool.get("name") == self.current_function_name
|
| 430 |
+
for tool in self.prev_tool_call_arr)
|
| 431 |
+
if not already_added:
|
| 432 |
+
self.prev_tool_call_arr.append({
|
| 433 |
+
"name": self.current_function_name,
|
| 434 |
+
"arguments":
|
| 435 |
+
"{}", # Placeholder, will be updated later
|
| 436 |
+
})
|
| 437 |
+
|
| 438 |
+
# Send header with function info
|
| 439 |
+
return DeltaMessage(tool_calls=[
|
| 440 |
+
DeltaToolCall(
|
| 441 |
+
index=self.current_tool_index,
|
| 442 |
+
id=self.current_tool_id,
|
| 443 |
+
function=DeltaFunctionCall(
|
| 444 |
+
name=self.current_function_name, arguments=""),
|
| 445 |
+
type="function",
|
| 446 |
+
)
|
| 447 |
+
])
|
| 448 |
+
return None
|
| 449 |
+
|
| 450 |
+
# We've sent header, now handle function body
|
| 451 |
+
if self.in_function:
|
| 452 |
+
# Send opening brace if not sent yet
|
| 453 |
+
if not self.json_started and self.parameter_prefix not in delta_text:
|
| 454 |
+
self.json_started = True
|
| 455 |
+
return DeltaMessage(tool_calls=[
|
| 456 |
+
DeltaToolCall(
|
| 457 |
+
index=self.current_tool_index,
|
| 458 |
+
function=DeltaFunctionCall(arguments="{"),
|
| 459 |
+
)
|
| 460 |
+
])
|
| 461 |
+
|
| 462 |
+
# Make sure json_started is set if we're processing parameters
|
| 463 |
+
if not self.json_started:
|
| 464 |
+
self.json_started = True
|
| 465 |
+
|
| 466 |
+
# Check for function end in accumulated text
|
| 467 |
+
if not self.json_closed and self.function_end_token in tool_text:
|
| 468 |
+
# Close JSON
|
| 469 |
+
self.json_closed = True
|
| 470 |
+
|
| 471 |
+
# Extract the complete tool call to update prev_tool_call_arr with final arguments
|
| 472 |
+
# Find the function content
|
| 473 |
+
func_start = tool_text.find(self.tool_call_prefix) + len(
|
| 474 |
+
self.tool_call_prefix)
|
| 475 |
+
func_content_end = tool_text.find(self.function_end_token,
|
| 476 |
+
func_start)
|
| 477 |
+
if func_content_end != -1:
|
| 478 |
+
func_content = tool_text[func_start:func_content_end]
|
| 479 |
+
# Parse to get the complete arguments
|
| 480 |
+
try:
|
| 481 |
+
parsed_tool = self._parse_xml_function_call(
|
| 482 |
+
func_content, self.streaming_request.tools
|
| 483 |
+
if self.streaming_request else None)
|
| 484 |
+
if parsed_tool:
|
| 485 |
+
# Update existing entry in prev_tool_call_arr with complete arguments
|
| 486 |
+
for i, tool in enumerate(self.prev_tool_call_arr):
|
| 487 |
+
if tool.get(
|
| 488 |
+
"name") == parsed_tool.function.name:
|
| 489 |
+
self.prev_tool_call_arr[i][
|
| 490 |
+
"arguments"] = parsed_tool.function.arguments
|
| 491 |
+
break
|
| 492 |
+
except Exception:
|
| 493 |
+
pass # Ignore parsing errors during streaming
|
| 494 |
+
|
| 495 |
+
result = DeltaMessage(tool_calls=[
|
| 496 |
+
DeltaToolCall(
|
| 497 |
+
index=self.current_tool_index,
|
| 498 |
+
function=DeltaFunctionCall(arguments="}"),
|
| 499 |
+
)
|
| 500 |
+
])
|
| 501 |
+
|
| 502 |
+
# Reset state for next tool
|
| 503 |
+
self.in_function = False
|
| 504 |
+
self.json_closed = True
|
| 505 |
+
self.accumulated_params = {}
|
| 506 |
+
|
| 507 |
+
return result
|
| 508 |
+
|
| 509 |
+
# Look for parameters
|
| 510 |
+
# Find all parameter starts
|
| 511 |
+
param_starts = []
|
| 512 |
+
idx = 0
|
| 513 |
+
while True:
|
| 514 |
+
idx = tool_text.find(self.parameter_prefix, idx)
|
| 515 |
+
if idx == -1:
|
| 516 |
+
break
|
| 517 |
+
param_starts.append(idx)
|
| 518 |
+
idx += len(self.parameter_prefix)
|
| 519 |
+
|
| 520 |
+
# Check if we should start a new parameter
|
| 521 |
+
if not self.in_param and self.param_count < len(param_starts):
|
| 522 |
+
|
| 523 |
+
if len(param_starts) > self.param_count:
|
| 524 |
+
# Process the next parameter
|
| 525 |
+
param_idx = param_starts[self.param_count]
|
| 526 |
+
param_start = param_idx + len(self.parameter_prefix)
|
| 527 |
+
remaining = tool_text[param_start:]
|
| 528 |
+
|
| 529 |
+
if ">" in remaining:
|
| 530 |
+
# We have the complete parameter name
|
| 531 |
+
name_end = remaining.find(">")
|
| 532 |
+
self.current_param_name = remaining[:name_end]
|
| 533 |
+
|
| 534 |
+
# Find the parameter value
|
| 535 |
+
value_start = param_start + name_end + 1
|
| 536 |
+
value_text = tool_text[value_start:]
|
| 537 |
+
if value_text.startswith("\n"):
|
| 538 |
+
value_text = value_text[1:]
|
| 539 |
+
|
| 540 |
+
# Find where this parameter ends
|
| 541 |
+
param_end_idx = value_text.find(
|
| 542 |
+
self.parameter_end_token)
|
| 543 |
+
if param_end_idx == -1:
|
| 544 |
+
# No closing tag, look for next parameter or function end
|
| 545 |
+
next_param_idx = value_text.find(
|
| 546 |
+
self.parameter_prefix)
|
| 547 |
+
func_end_idx = value_text.find(
|
| 548 |
+
self.function_end_token)
|
| 549 |
+
|
| 550 |
+
if next_param_idx != -1 and (func_end_idx == -1
|
| 551 |
+
or next_param_idx
|
| 552 |
+
< func_end_idx):
|
| 553 |
+
param_end_idx = next_param_idx
|
| 554 |
+
elif func_end_idx != -1:
|
| 555 |
+
param_end_idx = func_end_idx
|
| 556 |
+
else:
|
| 557 |
+
# Neither found, check if tool call is complete
|
| 558 |
+
if self.tool_call_end_token in tool_text:
|
| 559 |
+
# Tool call is complete, so parameter must be complete too
|
| 560 |
+
# Use all remaining text before function end as value
|
| 561 |
+
param_end_idx = len(value_text)
|
| 562 |
+
else:
|
| 563 |
+
# Still streaming, wait for more content
|
| 564 |
+
return None
|
| 565 |
+
|
| 566 |
+
if param_end_idx != -1:
|
| 567 |
+
# Complete parameter found
|
| 568 |
+
param_value = value_text[:param_end_idx]
|
| 569 |
+
if param_value.endswith("\n"):
|
| 570 |
+
param_value = param_value[:-1]
|
| 571 |
+
|
| 572 |
+
# Store raw value for later processing
|
| 573 |
+
self.accumulated_params[
|
| 574 |
+
self.current_param_name] = param_value
|
| 575 |
+
|
| 576 |
+
# Get parameter configuration for type conversion
|
| 577 |
+
param_config = self._get_arguments_config(
|
| 578 |
+
self.current_function_name,
|
| 579 |
+
self.streaming_request.tools
|
| 580 |
+
if self.streaming_request else None)
|
| 581 |
+
|
| 582 |
+
# Convert the parameter value to the appropriate type
|
| 583 |
+
converted_value = self._convert_param_value(
|
| 584 |
+
param_value, self.current_param_name,
|
| 585 |
+
param_config, self.current_function_name)
|
| 586 |
+
|
| 587 |
+
# Build JSON fragment based on the converted type
|
| 588 |
+
# Use json.dumps to properly serialize the value
|
| 589 |
+
serialized_value = json.dumps(converted_value,
|
| 590 |
+
ensure_ascii=False)
|
| 591 |
+
|
| 592 |
+
if self.param_count == 0:
|
| 593 |
+
json_fragment = f'"{self.current_param_name}": {serialized_value}'
|
| 594 |
+
else:
|
| 595 |
+
json_fragment = f', "{self.current_param_name}": {serialized_value}'
|
| 596 |
+
|
| 597 |
+
self.param_count += 1
|
| 598 |
+
|
| 599 |
+
return DeltaMessage(tool_calls=[
|
| 600 |
+
DeltaToolCall(
|
| 601 |
+
index=self.current_tool_index,
|
| 602 |
+
function=DeltaFunctionCall(
|
| 603 |
+
arguments=json_fragment),
|
| 604 |
+
)
|
| 605 |
+
])
|
| 606 |
+
|
| 607 |
+
# Continue parameter value - Not used in the current implementation
|
| 608 |
+
# since we process complete parameters above
|
| 609 |
+
if self.in_param:
|
| 610 |
+
if self.parameter_end_token in delta_text:
|
| 611 |
+
# End of parameter
|
| 612 |
+
end_idx = delta_text.find(self.parameter_end_token)
|
| 613 |
+
value_chunk = delta_text[:end_idx]
|
| 614 |
+
|
| 615 |
+
# Skip past > if at start
|
| 616 |
+
if not self.current_param_value and ">" in value_chunk:
|
| 617 |
+
gt_idx = value_chunk.find(">")
|
| 618 |
+
value_chunk = value_chunk[gt_idx + 1:]
|
| 619 |
+
|
| 620 |
+
if not self.current_param_value and value_chunk.startswith(
|
| 621 |
+
"\n"):
|
| 622 |
+
value_chunk = value_chunk[1:]
|
| 623 |
+
|
| 624 |
+
# Store complete value
|
| 625 |
+
full_value = self.current_param_value + value_chunk
|
| 626 |
+
self.accumulated_params[
|
| 627 |
+
self.current_param_name] = full_value
|
| 628 |
+
|
| 629 |
+
# Get parameter configuration for type conversion
|
| 630 |
+
param_config = self._get_arguments_config(
|
| 631 |
+
self.current_function_name,
|
| 632 |
+
self.streaming_request.tools
|
| 633 |
+
if self.streaming_request else None)
|
| 634 |
+
|
| 635 |
+
# Convert the parameter value to the appropriate type
|
| 636 |
+
converted_value = self._convert_param_value(
|
| 637 |
+
full_value, self.current_param_name, param_config,
|
| 638 |
+
self.current_function_name)
|
| 639 |
+
|
| 640 |
+
# Serialize the converted value
|
| 641 |
+
serialized_value = json.dumps(converted_value,
|
| 642 |
+
ensure_ascii=False)
|
| 643 |
+
|
| 644 |
+
# Since we've been streaming the quoted version, we need to close it properly
|
| 645 |
+
# This is complex - for now just complete the value
|
| 646 |
+
self.in_param = False
|
| 647 |
+
self.current_param_value = ""
|
| 648 |
+
|
| 649 |
+
# Just close the current parameter string
|
| 650 |
+
return DeltaMessage(tool_calls=[
|
| 651 |
+
DeltaToolCall(
|
| 652 |
+
index=self.current_tool_index,
|
| 653 |
+
function=DeltaFunctionCall(
|
| 654 |
+
arguments='"'), # Close the string quote
|
| 655 |
+
)
|
| 656 |
+
])
|
| 657 |
+
else:
|
| 658 |
+
# Continue accumulating value
|
| 659 |
+
value_chunk = delta_text
|
| 660 |
+
|
| 661 |
+
# Handle first chunk after param name
|
| 662 |
+
if not self.current_param_value and ">" in value_chunk:
|
| 663 |
+
gt_idx = value_chunk.find(">")
|
| 664 |
+
value_chunk = value_chunk[gt_idx + 1:]
|
| 665 |
+
|
| 666 |
+
if not self.current_param_value and value_chunk.startswith(
|
| 667 |
+
"\n"):
|
| 668 |
+
value_chunk = value_chunk[1:]
|
| 669 |
+
|
| 670 |
+
if value_chunk:
|
| 671 |
+
# Stream the escaped delta
|
| 672 |
+
prev_escaped = json.dumps(
|
| 673 |
+
self.current_param_value, ensure_ascii=False
|
| 674 |
+
)[1:-1] if self.current_param_value else ""
|
| 675 |
+
self.current_param_value += value_chunk
|
| 676 |
+
full_escaped = json.dumps(self.current_param_value,
|
| 677 |
+
ensure_ascii=False)[1:-1]
|
| 678 |
+
delta_escaped = full_escaped[len(prev_escaped):]
|
| 679 |
+
|
| 680 |
+
if delta_escaped:
|
| 681 |
+
return DeltaMessage(tool_calls=[
|
| 682 |
+
DeltaToolCall(
|
| 683 |
+
index=self.current_tool_index,
|
| 684 |
+
function=DeltaFunctionCall(
|
| 685 |
+
arguments=delta_escaped),
|
| 686 |
+
)
|
| 687 |
+
])
|
| 688 |
+
|
| 689 |
+
return None
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1048576,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|