Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/31349551d90c7606f325fe0f11bbb8bd5fa0d7c7.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/4783fe10ac3adce15ac8f358ef5462739852c569.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/49b0e8d0ee7e655434942233b4b0ab2104d5247e.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/85c7de5b6114edc061271408a62af51fd7449020.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/ba3e8d9206508daab666e1aaa9dcc9c435bfa541.lock +0 -0
- .locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/cc8cf0649efea42a8c099d852b1525fcfc42c222.lock +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/added_tokens.json +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/preprocessor_config.json +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/special_tokens_map.json +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/31349551d90c7606f325fe0f11bbb8bd5fa0d7c7 +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/4783fe10ac3adce15ac8f358ef5462739852c569 +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/49b0e8d0ee7e655434942233b4b0ab2104d5247e +117 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/85c7de5b6114edc061271408a62af51fd7449020 +195 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +3 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/ba3e8d9206508daab666e1aaa9dcc9c435bfa541 +12 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/cc8cf0649efea42a8c099d852b1525fcfc42c222 +239 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/refs/main +1 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/chat_template.jinja +117 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/config.json +195 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/generation_config.json +12 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/merges.txt +0 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/tokenizer.json +3 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/tokenizer_config.json +239 -0
- models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/31349551d90c7606f325fe0f11bbb8bd5fa0d7c7.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/4783fe10ac3adce15ac8f358ef5462739852c569.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/49b0e8d0ee7e655434942233b4b0ab2104d5247e.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/85c7de5b6114edc061271408a62af51fd7449020.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/ba3e8d9206508daab666e1aaa9dcc9c435bfa541.lock
ADDED
|
File without changes
|
.locks/models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/cc8cf0649efea42a8c099d852b1525fcfc42c222.lock
ADDED
|
File without changes
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/added_tokens.json
ADDED
|
File without changes
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/preprocessor_config.json
ADDED
|
File without changes
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/.no_exist/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/special_tokens_map.json
ADDED
|
File without changes
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/31349551d90c7606f325fe0f11bbb8bd5fa0d7c7
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/4783fe10ac3adce15ac8f358ef5462739852c569
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/49b0e8d0ee7e655434942233b4b0ab2104d5247e
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 %}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/85c7de5b6114edc061271408a62af51fd7449020
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5472,
|
| 14 |
+
"max_position_embeddings": 262144,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"mlp_only_layers": [],
|
| 17 |
+
"model_type": "qwen3_moe",
|
| 18 |
+
"moe_intermediate_size": 768,
|
| 19 |
+
"norm_topk_prob": true,
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_experts": 128,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"num_hidden_layers": 48,
|
| 24 |
+
"num_key_value_heads": 4,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"qkv_bias": false,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"activation_scheme": "dynamic",
|
| 29 |
+
"modules_to_not_convert": [
|
| 30 |
+
"lm_head",
|
| 31 |
+
"model.layers.0.input_layernorm",
|
| 32 |
+
"model.layers.0.mlp.gate",
|
| 33 |
+
"model.layers.0.post_attention_layernorm",
|
| 34 |
+
"model.layers.1.input_layernorm",
|
| 35 |
+
"model.layers.1.mlp.gate",
|
| 36 |
+
"model.layers.1.post_attention_layernorm",
|
| 37 |
+
"model.layers.2.input_layernorm",
|
| 38 |
+
"model.layers.2.mlp.gate",
|
| 39 |
+
"model.layers.2.post_attention_layernorm",
|
| 40 |
+
"model.layers.3.input_layernorm",
|
| 41 |
+
"model.layers.3.mlp.gate",
|
| 42 |
+
"model.layers.3.post_attention_layernorm",
|
| 43 |
+
"model.layers.4.input_layernorm",
|
| 44 |
+
"model.layers.4.mlp.gate",
|
| 45 |
+
"model.layers.4.post_attention_layernorm",
|
| 46 |
+
"model.layers.5.input_layernorm",
|
| 47 |
+
"model.layers.5.mlp.gate",
|
| 48 |
+
"model.layers.5.post_attention_layernorm",
|
| 49 |
+
"model.layers.6.input_layernorm",
|
| 50 |
+
"model.layers.6.mlp.gate",
|
| 51 |
+
"model.layers.6.post_attention_layernorm",
|
| 52 |
+
"model.layers.7.input_layernorm",
|
| 53 |
+
"model.layers.7.mlp.gate",
|
| 54 |
+
"model.layers.7.post_attention_layernorm",
|
| 55 |
+
"model.layers.8.input_layernorm",
|
| 56 |
+
"model.layers.8.mlp.gate",
|
| 57 |
+
"model.layers.8.post_attention_layernorm",
|
| 58 |
+
"model.layers.9.input_layernorm",
|
| 59 |
+
"model.layers.9.mlp.gate",
|
| 60 |
+
"model.layers.9.post_attention_layernorm",
|
| 61 |
+
"model.layers.10.input_layernorm",
|
| 62 |
+
"model.layers.10.mlp.gate",
|
| 63 |
+
"model.layers.10.post_attention_layernorm",
|
| 64 |
+
"model.layers.11.input_layernorm",
|
| 65 |
+
"model.layers.11.mlp.gate",
|
| 66 |
+
"model.layers.11.post_attention_layernorm",
|
| 67 |
+
"model.layers.12.input_layernorm",
|
| 68 |
+
"model.layers.12.mlp.gate",
|
| 69 |
+
"model.layers.12.post_attention_layernorm",
|
| 70 |
+
"model.layers.13.input_layernorm",
|
| 71 |
+
"model.layers.13.mlp.gate",
|
| 72 |
+
"model.layers.13.post_attention_layernorm",
|
| 73 |
+
"model.layers.14.input_layernorm",
|
| 74 |
+
"model.layers.14.mlp.gate",
|
| 75 |
+
"model.layers.14.post_attention_layernorm",
|
| 76 |
+
"model.layers.15.input_layernorm",
|
| 77 |
+
"model.layers.15.mlp.gate",
|
| 78 |
+
"model.layers.15.post_attention_layernorm",
|
| 79 |
+
"model.layers.16.input_layernorm",
|
| 80 |
+
"model.layers.16.mlp.gate",
|
| 81 |
+
"model.layers.16.post_attention_layernorm",
|
| 82 |
+
"model.layers.17.input_layernorm",
|
| 83 |
+
"model.layers.17.mlp.gate",
|
| 84 |
+
"model.layers.17.post_attention_layernorm",
|
| 85 |
+
"model.layers.18.input_layernorm",
|
| 86 |
+
"model.layers.18.mlp.gate",
|
| 87 |
+
"model.layers.18.post_attention_layernorm",
|
| 88 |
+
"model.layers.19.input_layernorm",
|
| 89 |
+
"model.layers.19.mlp.gate",
|
| 90 |
+
"model.layers.19.post_attention_layernorm",
|
| 91 |
+
"model.layers.20.input_layernorm",
|
| 92 |
+
"model.layers.20.mlp.gate",
|
| 93 |
+
"model.layers.20.post_attention_layernorm",
|
| 94 |
+
"model.layers.21.input_layernorm",
|
| 95 |
+
"model.layers.21.mlp.gate",
|
| 96 |
+
"model.layers.21.post_attention_layernorm",
|
| 97 |
+
"model.layers.22.input_layernorm",
|
| 98 |
+
"model.layers.22.mlp.gate",
|
| 99 |
+
"model.layers.22.post_attention_layernorm",
|
| 100 |
+
"model.layers.23.input_layernorm",
|
| 101 |
+
"model.layers.23.mlp.gate",
|
| 102 |
+
"model.layers.23.post_attention_layernorm",
|
| 103 |
+
"model.layers.24.input_layernorm",
|
| 104 |
+
"model.layers.24.mlp.gate",
|
| 105 |
+
"model.layers.24.post_attention_layernorm",
|
| 106 |
+
"model.layers.25.input_layernorm",
|
| 107 |
+
"model.layers.25.mlp.gate",
|
| 108 |
+
"model.layers.25.post_attention_layernorm",
|
| 109 |
+
"model.layers.26.input_layernorm",
|
| 110 |
+
"model.layers.26.mlp.gate",
|
| 111 |
+
"model.layers.26.post_attention_layernorm",
|
| 112 |
+
"model.layers.27.input_layernorm",
|
| 113 |
+
"model.layers.27.mlp.gate",
|
| 114 |
+
"model.layers.27.post_attention_layernorm",
|
| 115 |
+
"model.layers.28.input_layernorm",
|
| 116 |
+
"model.layers.28.mlp.gate",
|
| 117 |
+
"model.layers.28.post_attention_layernorm",
|
| 118 |
+
"model.layers.29.input_layernorm",
|
| 119 |
+
"model.layers.29.mlp.gate",
|
| 120 |
+
"model.layers.29.post_attention_layernorm",
|
| 121 |
+
"model.layers.30.input_layernorm",
|
| 122 |
+
"model.layers.30.mlp.gate",
|
| 123 |
+
"model.layers.30.post_attention_layernorm",
|
| 124 |
+
"model.layers.31.input_layernorm",
|
| 125 |
+
"model.layers.31.mlp.gate",
|
| 126 |
+
"model.layers.31.post_attention_layernorm",
|
| 127 |
+
"model.layers.32.input_layernorm",
|
| 128 |
+
"model.layers.32.mlp.gate",
|
| 129 |
+
"model.layers.32.post_attention_layernorm",
|
| 130 |
+
"model.layers.33.input_layernorm",
|
| 131 |
+
"model.layers.33.mlp.gate",
|
| 132 |
+
"model.layers.33.post_attention_layernorm",
|
| 133 |
+
"model.layers.34.input_layernorm",
|
| 134 |
+
"model.layers.34.mlp.gate",
|
| 135 |
+
"model.layers.34.post_attention_layernorm",
|
| 136 |
+
"model.layers.35.input_layernorm",
|
| 137 |
+
"model.layers.35.mlp.gate",
|
| 138 |
+
"model.layers.35.post_attention_layernorm",
|
| 139 |
+
"model.layers.36.input_layernorm",
|
| 140 |
+
"model.layers.36.mlp.gate",
|
| 141 |
+
"model.layers.36.post_attention_layernorm",
|
| 142 |
+
"model.layers.37.input_layernorm",
|
| 143 |
+
"model.layers.37.mlp.gate",
|
| 144 |
+
"model.layers.37.post_attention_layernorm",
|
| 145 |
+
"model.layers.38.input_layernorm",
|
| 146 |
+
"model.layers.38.mlp.gate",
|
| 147 |
+
"model.layers.38.post_attention_layernorm",
|
| 148 |
+
"model.layers.39.input_layernorm",
|
| 149 |
+
"model.layers.39.mlp.gate",
|
| 150 |
+
"model.layers.39.post_attention_layernorm",
|
| 151 |
+
"model.layers.40.input_layernorm",
|
| 152 |
+
"model.layers.40.mlp.gate",
|
| 153 |
+
"model.layers.40.post_attention_layernorm",
|
| 154 |
+
"model.layers.41.input_layernorm",
|
| 155 |
+
"model.layers.41.mlp.gate",
|
| 156 |
+
"model.layers.41.post_attention_layernorm",
|
| 157 |
+
"model.layers.42.input_layernorm",
|
| 158 |
+
"model.layers.42.mlp.gate",
|
| 159 |
+
"model.layers.42.post_attention_layernorm",
|
| 160 |
+
"model.layers.43.input_layernorm",
|
| 161 |
+
"model.layers.43.mlp.gate",
|
| 162 |
+
"model.layers.43.post_attention_layernorm",
|
| 163 |
+
"model.layers.44.input_layernorm",
|
| 164 |
+
"model.layers.44.mlp.gate",
|
| 165 |
+
"model.layers.44.post_attention_layernorm",
|
| 166 |
+
"model.layers.45.input_layernorm",
|
| 167 |
+
"model.layers.45.mlp.gate",
|
| 168 |
+
"model.layers.45.post_attention_layernorm",
|
| 169 |
+
"model.layers.46.input_layernorm",
|
| 170 |
+
"model.layers.46.mlp.gate",
|
| 171 |
+
"model.layers.46.post_attention_layernorm",
|
| 172 |
+
"model.layers.47.input_layernorm",
|
| 173 |
+
"model.layers.47.mlp.gate",
|
| 174 |
+
"model.layers.47.post_attention_layernorm"
|
| 175 |
+
],
|
| 176 |
+
"quant_method": "fp8",
|
| 177 |
+
"weight_block_size": [
|
| 178 |
+
128,
|
| 179 |
+
128
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
"rms_norm_eps": 1e-06,
|
| 183 |
+
"rope_scaling": null,
|
| 184 |
+
"rope_theta": 10000000,
|
| 185 |
+
"router_aux_loss_coef": 0.0,
|
| 186 |
+
"shared_expert_intermediate_size": 0,
|
| 187 |
+
"sliding_window": null,
|
| 188 |
+
"tie_word_embeddings": false,
|
| 189 |
+
"torch_dtype": "bfloat16",
|
| 190 |
+
"transformers_version": "4.51.3",
|
| 191 |
+
"use_cache": true,
|
| 192 |
+
"use_qk_norm": true,
|
| 193 |
+
"use_sliding_window": false,
|
| 194 |
+
"vocab_size": 151936
|
| 195 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/ba3e8d9206508daab666e1aaa9dcc9c435bfa541
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 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/blobs/cc8cf0649efea42a8c099d852b1525fcfc42c222
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"151665": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"151666": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"151667": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"151668": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
}
|
| 212 |
+
},
|
| 213 |
+
"additional_special_tokens": [
|
| 214 |
+
"<|im_start|>",
|
| 215 |
+
"<|im_end|>",
|
| 216 |
+
"<|object_ref_start|>",
|
| 217 |
+
"<|object_ref_end|>",
|
| 218 |
+
"<|box_start|>",
|
| 219 |
+
"<|box_end|>",
|
| 220 |
+
"<|quad_start|>",
|
| 221 |
+
"<|quad_end|>",
|
| 222 |
+
"<|vision_start|>",
|
| 223 |
+
"<|vision_end|>",
|
| 224 |
+
"<|vision_pad|>",
|
| 225 |
+
"<|image_pad|>",
|
| 226 |
+
"<|video_pad|>"
|
| 227 |
+
],
|
| 228 |
+
"bos_token": null,
|
| 229 |
+
"chat_template": "{% macro render_extra_keys(json_dict, handled_keys) %}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{% endmacro %}\n\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{%- if not tools is defined %}\n {%- set tools = [] %}\n{%- endif %}\n\n{%- if system_message is defined %}\n {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- \"<|im_start|>system\\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks.\" }}\n {%- endif %}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n {{- \"\\n\\n# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {{- \"<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n {%- if tool.description is defined %}\n {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n {%- endif %}\n {{- '\\n<parameters>' }}\n {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- '\\n<parameter>' }}\n {{- '\\n<name>' ~ param_name ~ '</name>' }}\n {%- if param_fields.type is defined %}\n {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n {%- endif %}\n {%- if param_fields.description is defined %}\n {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n {%- endif %}\n {%- set handled_keys = ['name', 'type', 'description'] %}\n {{- render_extra_keys(param_fields, handled_keys) }}\n {{- '\\n</parameter>' }}\n {%- endfor %}\n {%- endif %}\n {% set handled_keys = ['type', 'properties'] %}\n {{- render_extra_keys(tool.parameters, handled_keys) }}\n {{- '\\n</parameters>' }}\n {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n {{- render_extra_keys(tool, handled_keys) }}\n {{- '\\n</function>' }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n{%- endif %}\n{%- if system_message is defined %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in loop_messages %}\n {%- if message.role == \"assistant\" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}\n {{- '\\n' + message.content | trim + '\\n' }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"user\" or message.role == \"system\" or message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"model_max_length": 1048576,
|
| 234 |
+
"pad_token": "<|endoftext|>",
|
| 235 |
+
"split_special_tokens": false,
|
| 236 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 237 |
+
"unk_token": null,
|
| 238 |
+
"add_bos_token": false
|
| 239 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
e8ab3f2db9e388999a004eea5a31c16a8b517bc0
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/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 %}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5472,
|
| 14 |
+
"max_position_embeddings": 262144,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"mlp_only_layers": [],
|
| 17 |
+
"model_type": "qwen3_moe",
|
| 18 |
+
"moe_intermediate_size": 768,
|
| 19 |
+
"norm_topk_prob": true,
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_experts": 128,
|
| 22 |
+
"num_experts_per_tok": 8,
|
| 23 |
+
"num_hidden_layers": 48,
|
| 24 |
+
"num_key_value_heads": 4,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"qkv_bias": false,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"activation_scheme": "dynamic",
|
| 29 |
+
"modules_to_not_convert": [
|
| 30 |
+
"lm_head",
|
| 31 |
+
"model.layers.0.input_layernorm",
|
| 32 |
+
"model.layers.0.mlp.gate",
|
| 33 |
+
"model.layers.0.post_attention_layernorm",
|
| 34 |
+
"model.layers.1.input_layernorm",
|
| 35 |
+
"model.layers.1.mlp.gate",
|
| 36 |
+
"model.layers.1.post_attention_layernorm",
|
| 37 |
+
"model.layers.2.input_layernorm",
|
| 38 |
+
"model.layers.2.mlp.gate",
|
| 39 |
+
"model.layers.2.post_attention_layernorm",
|
| 40 |
+
"model.layers.3.input_layernorm",
|
| 41 |
+
"model.layers.3.mlp.gate",
|
| 42 |
+
"model.layers.3.post_attention_layernorm",
|
| 43 |
+
"model.layers.4.input_layernorm",
|
| 44 |
+
"model.layers.4.mlp.gate",
|
| 45 |
+
"model.layers.4.post_attention_layernorm",
|
| 46 |
+
"model.layers.5.input_layernorm",
|
| 47 |
+
"model.layers.5.mlp.gate",
|
| 48 |
+
"model.layers.5.post_attention_layernorm",
|
| 49 |
+
"model.layers.6.input_layernorm",
|
| 50 |
+
"model.layers.6.mlp.gate",
|
| 51 |
+
"model.layers.6.post_attention_layernorm",
|
| 52 |
+
"model.layers.7.input_layernorm",
|
| 53 |
+
"model.layers.7.mlp.gate",
|
| 54 |
+
"model.layers.7.post_attention_layernorm",
|
| 55 |
+
"model.layers.8.input_layernorm",
|
| 56 |
+
"model.layers.8.mlp.gate",
|
| 57 |
+
"model.layers.8.post_attention_layernorm",
|
| 58 |
+
"model.layers.9.input_layernorm",
|
| 59 |
+
"model.layers.9.mlp.gate",
|
| 60 |
+
"model.layers.9.post_attention_layernorm",
|
| 61 |
+
"model.layers.10.input_layernorm",
|
| 62 |
+
"model.layers.10.mlp.gate",
|
| 63 |
+
"model.layers.10.post_attention_layernorm",
|
| 64 |
+
"model.layers.11.input_layernorm",
|
| 65 |
+
"model.layers.11.mlp.gate",
|
| 66 |
+
"model.layers.11.post_attention_layernorm",
|
| 67 |
+
"model.layers.12.input_layernorm",
|
| 68 |
+
"model.layers.12.mlp.gate",
|
| 69 |
+
"model.layers.12.post_attention_layernorm",
|
| 70 |
+
"model.layers.13.input_layernorm",
|
| 71 |
+
"model.layers.13.mlp.gate",
|
| 72 |
+
"model.layers.13.post_attention_layernorm",
|
| 73 |
+
"model.layers.14.input_layernorm",
|
| 74 |
+
"model.layers.14.mlp.gate",
|
| 75 |
+
"model.layers.14.post_attention_layernorm",
|
| 76 |
+
"model.layers.15.input_layernorm",
|
| 77 |
+
"model.layers.15.mlp.gate",
|
| 78 |
+
"model.layers.15.post_attention_layernorm",
|
| 79 |
+
"model.layers.16.input_layernorm",
|
| 80 |
+
"model.layers.16.mlp.gate",
|
| 81 |
+
"model.layers.16.post_attention_layernorm",
|
| 82 |
+
"model.layers.17.input_layernorm",
|
| 83 |
+
"model.layers.17.mlp.gate",
|
| 84 |
+
"model.layers.17.post_attention_layernorm",
|
| 85 |
+
"model.layers.18.input_layernorm",
|
| 86 |
+
"model.layers.18.mlp.gate",
|
| 87 |
+
"model.layers.18.post_attention_layernorm",
|
| 88 |
+
"model.layers.19.input_layernorm",
|
| 89 |
+
"model.layers.19.mlp.gate",
|
| 90 |
+
"model.layers.19.post_attention_layernorm",
|
| 91 |
+
"model.layers.20.input_layernorm",
|
| 92 |
+
"model.layers.20.mlp.gate",
|
| 93 |
+
"model.layers.20.post_attention_layernorm",
|
| 94 |
+
"model.layers.21.input_layernorm",
|
| 95 |
+
"model.layers.21.mlp.gate",
|
| 96 |
+
"model.layers.21.post_attention_layernorm",
|
| 97 |
+
"model.layers.22.input_layernorm",
|
| 98 |
+
"model.layers.22.mlp.gate",
|
| 99 |
+
"model.layers.22.post_attention_layernorm",
|
| 100 |
+
"model.layers.23.input_layernorm",
|
| 101 |
+
"model.layers.23.mlp.gate",
|
| 102 |
+
"model.layers.23.post_attention_layernorm",
|
| 103 |
+
"model.layers.24.input_layernorm",
|
| 104 |
+
"model.layers.24.mlp.gate",
|
| 105 |
+
"model.layers.24.post_attention_layernorm",
|
| 106 |
+
"model.layers.25.input_layernorm",
|
| 107 |
+
"model.layers.25.mlp.gate",
|
| 108 |
+
"model.layers.25.post_attention_layernorm",
|
| 109 |
+
"model.layers.26.input_layernorm",
|
| 110 |
+
"model.layers.26.mlp.gate",
|
| 111 |
+
"model.layers.26.post_attention_layernorm",
|
| 112 |
+
"model.layers.27.input_layernorm",
|
| 113 |
+
"model.layers.27.mlp.gate",
|
| 114 |
+
"model.layers.27.post_attention_layernorm",
|
| 115 |
+
"model.layers.28.input_layernorm",
|
| 116 |
+
"model.layers.28.mlp.gate",
|
| 117 |
+
"model.layers.28.post_attention_layernorm",
|
| 118 |
+
"model.layers.29.input_layernorm",
|
| 119 |
+
"model.layers.29.mlp.gate",
|
| 120 |
+
"model.layers.29.post_attention_layernorm",
|
| 121 |
+
"model.layers.30.input_layernorm",
|
| 122 |
+
"model.layers.30.mlp.gate",
|
| 123 |
+
"model.layers.30.post_attention_layernorm",
|
| 124 |
+
"model.layers.31.input_layernorm",
|
| 125 |
+
"model.layers.31.mlp.gate",
|
| 126 |
+
"model.layers.31.post_attention_layernorm",
|
| 127 |
+
"model.layers.32.input_layernorm",
|
| 128 |
+
"model.layers.32.mlp.gate",
|
| 129 |
+
"model.layers.32.post_attention_layernorm",
|
| 130 |
+
"model.layers.33.input_layernorm",
|
| 131 |
+
"model.layers.33.mlp.gate",
|
| 132 |
+
"model.layers.33.post_attention_layernorm",
|
| 133 |
+
"model.layers.34.input_layernorm",
|
| 134 |
+
"model.layers.34.mlp.gate",
|
| 135 |
+
"model.layers.34.post_attention_layernorm",
|
| 136 |
+
"model.layers.35.input_layernorm",
|
| 137 |
+
"model.layers.35.mlp.gate",
|
| 138 |
+
"model.layers.35.post_attention_layernorm",
|
| 139 |
+
"model.layers.36.input_layernorm",
|
| 140 |
+
"model.layers.36.mlp.gate",
|
| 141 |
+
"model.layers.36.post_attention_layernorm",
|
| 142 |
+
"model.layers.37.input_layernorm",
|
| 143 |
+
"model.layers.37.mlp.gate",
|
| 144 |
+
"model.layers.37.post_attention_layernorm",
|
| 145 |
+
"model.layers.38.input_layernorm",
|
| 146 |
+
"model.layers.38.mlp.gate",
|
| 147 |
+
"model.layers.38.post_attention_layernorm",
|
| 148 |
+
"model.layers.39.input_layernorm",
|
| 149 |
+
"model.layers.39.mlp.gate",
|
| 150 |
+
"model.layers.39.post_attention_layernorm",
|
| 151 |
+
"model.layers.40.input_layernorm",
|
| 152 |
+
"model.layers.40.mlp.gate",
|
| 153 |
+
"model.layers.40.post_attention_layernorm",
|
| 154 |
+
"model.layers.41.input_layernorm",
|
| 155 |
+
"model.layers.41.mlp.gate",
|
| 156 |
+
"model.layers.41.post_attention_layernorm",
|
| 157 |
+
"model.layers.42.input_layernorm",
|
| 158 |
+
"model.layers.42.mlp.gate",
|
| 159 |
+
"model.layers.42.post_attention_layernorm",
|
| 160 |
+
"model.layers.43.input_layernorm",
|
| 161 |
+
"model.layers.43.mlp.gate",
|
| 162 |
+
"model.layers.43.post_attention_layernorm",
|
| 163 |
+
"model.layers.44.input_layernorm",
|
| 164 |
+
"model.layers.44.mlp.gate",
|
| 165 |
+
"model.layers.44.post_attention_layernorm",
|
| 166 |
+
"model.layers.45.input_layernorm",
|
| 167 |
+
"model.layers.45.mlp.gate",
|
| 168 |
+
"model.layers.45.post_attention_layernorm",
|
| 169 |
+
"model.layers.46.input_layernorm",
|
| 170 |
+
"model.layers.46.mlp.gate",
|
| 171 |
+
"model.layers.46.post_attention_layernorm",
|
| 172 |
+
"model.layers.47.input_layernorm",
|
| 173 |
+
"model.layers.47.mlp.gate",
|
| 174 |
+
"model.layers.47.post_attention_layernorm"
|
| 175 |
+
],
|
| 176 |
+
"quant_method": "fp8",
|
| 177 |
+
"weight_block_size": [
|
| 178 |
+
128,
|
| 179 |
+
128
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
"rms_norm_eps": 1e-06,
|
| 183 |
+
"rope_scaling": null,
|
| 184 |
+
"rope_theta": 10000000,
|
| 185 |
+
"router_aux_loss_coef": 0.0,
|
| 186 |
+
"shared_expert_intermediate_size": 0,
|
| 187 |
+
"sliding_window": null,
|
| 188 |
+
"tie_word_embeddings": false,
|
| 189 |
+
"torch_dtype": "bfloat16",
|
| 190 |
+
"transformers_version": "4.51.3",
|
| 191 |
+
"use_cache": true,
|
| 192 |
+
"use_qk_norm": true,
|
| 193 |
+
"use_sliding_window": false,
|
| 194 |
+
"vocab_size": 151936
|
| 195 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/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 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"151665": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"151666": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"151667": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"151668": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
}
|
| 212 |
+
},
|
| 213 |
+
"additional_special_tokens": [
|
| 214 |
+
"<|im_start|>",
|
| 215 |
+
"<|im_end|>",
|
| 216 |
+
"<|object_ref_start|>",
|
| 217 |
+
"<|object_ref_end|>",
|
| 218 |
+
"<|box_start|>",
|
| 219 |
+
"<|box_end|>",
|
| 220 |
+
"<|quad_start|>",
|
| 221 |
+
"<|quad_end|>",
|
| 222 |
+
"<|vision_start|>",
|
| 223 |
+
"<|vision_end|>",
|
| 224 |
+
"<|vision_pad|>",
|
| 225 |
+
"<|image_pad|>",
|
| 226 |
+
"<|video_pad|>"
|
| 227 |
+
],
|
| 228 |
+
"bos_token": null,
|
| 229 |
+
"chat_template": "{% macro render_extra_keys(json_dict, handled_keys) %}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{% endmacro %}\n\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{%- if not tools is defined %}\n {%- set tools = [] %}\n{%- endif %}\n\n{%- if system_message is defined %}\n {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- \"<|im_start|>system\\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks.\" }}\n {%- endif %}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n {{- \"\\n\\n# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {{- \"<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n {%- if tool.description is defined %}\n {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n {%- endif %}\n {{- '\\n<parameters>' }}\n {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- '\\n<parameter>' }}\n {{- '\\n<name>' ~ param_name ~ '</name>' }}\n {%- if param_fields.type is defined %}\n {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n {%- endif %}\n {%- if param_fields.description is defined %}\n {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n {%- endif %}\n {%- set handled_keys = ['name', 'type', 'description'] %}\n {{- render_extra_keys(param_fields, handled_keys) }}\n {{- '\\n</parameter>' }}\n {%- endfor %}\n {%- endif %}\n {% set handled_keys = ['type', 'properties'] %}\n {{- render_extra_keys(tool.parameters, handled_keys) }}\n {{- '\\n</parameters>' }}\n {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n {{- render_extra_keys(tool, handled_keys) }}\n {{- '\\n</function>' }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n{%- endif %}\n{%- if system_message is defined %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in loop_messages %}\n {%- if message.role == \"assistant\" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}\n {{- '\\n' + message.content | trim + '\\n' }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"user\" or message.role == \"system\" or message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"model_max_length": 1048576,
|
| 234 |
+
"pad_token": "<|endoftext|>",
|
| 235 |
+
"split_special_tokens": false,
|
| 236 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 237 |
+
"unk_token": null,
|
| 238 |
+
"add_bos_token": false
|
| 239 |
+
}
|
models--Qwen--Qwen3-Coder-30B-A3B-Instruct-FP8/snapshots/e8ab3f2db9e388999a004eea5a31c16a8b517bc0/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|