Add files using upload-large-folder tool
Browse files- README.md +13 -2
- chat_template.jinja +85 -0
- config.json +4 -3
- generation_config.json +13 -12
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +6 -4
README.md
CHANGED
@@ -1,3 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Qwen3-30B-A3B
|
2 |
|
3 |
## Qwen3 Highlights
|
@@ -19,6 +25,8 @@ Qwen3 is the latest generation of large language models in Qwen series, offering
|
|
19 |
- Number of Paramaters (Non-Embedding): 29.9B
|
20 |
- Number of Layers: 48
|
21 |
- Number of Attention Heads (GQA): 32 for Q and 4 for KV
|
|
|
|
|
22 |
- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).
|
23 |
|
24 |
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
@@ -202,7 +210,6 @@ Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https
|
|
202 |
|
203 |
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
|
204 |
```python
|
205 |
-
import os
|
206 |
from qwen_agent.agents import Assistant
|
207 |
|
208 |
# Define LLM
|
@@ -232,6 +239,10 @@ tools = [
|
|
232 |
'command': 'uvx',
|
233 |
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
|
234 |
},
|
|
|
|
|
|
|
|
|
235 |
}
|
236 |
},
|
237 |
'code_interpreter', # Built-in tools
|
@@ -241,7 +252,7 @@ tools = [
|
|
241 |
bot = Assistant(llm=llm_cfg, function_list=tools)
|
242 |
|
243 |
# Streaming generation
|
244 |
-
messages = [{'role': 'user', 'content': '
|
245 |
for responses in bot.run(messages=messages):
|
246 |
pass
|
247 |
print(responses)
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- unsloth
|
4 |
+
base_model:
|
5 |
+
- Qwen/Qwen3-30B-A3B
|
6 |
+
---
|
7 |
# Qwen3-30B-A3B
|
8 |
|
9 |
## Qwen3 Highlights
|
|
|
25 |
- Number of Paramaters (Non-Embedding): 29.9B
|
26 |
- Number of Layers: 48
|
27 |
- Number of Attention Heads (GQA): 32 for Q and 4 for KV
|
28 |
+
- Number of Experts: 128
|
29 |
+
- Number of Activated Experts: 8
|
30 |
- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).
|
31 |
|
32 |
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
|
|
210 |
|
211 |
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
|
212 |
```python
|
|
|
213 |
from qwen_agent.agents import Assistant
|
214 |
|
215 |
# Define LLM
|
|
|
239 |
'command': 'uvx',
|
240 |
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
|
241 |
},
|
242 |
+
"fetch": {
|
243 |
+
"command": "uvx",
|
244 |
+
"args": ["mcp-server-fetch"]
|
245 |
+
}
|
246 |
}
|
247 |
},
|
248 |
'code_interpreter', # Built-in tools
|
|
|
252 |
bot = Assistant(llm=llm_cfg, function_list=tools)
|
253 |
|
254 |
# Streaming generation
|
255 |
+
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
|
256 |
for responses in bot.run(messages=messages):
|
257 |
pass
|
258 |
print(responses)
|
chat_template.jinja
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools %}
|
2 |
+
{{- '<|im_start|>system\n' }}
|
3 |
+
{%- if messages[0].role == 'system' %}
|
4 |
+
{{- messages[0].content + '\n\n' }}
|
5 |
+
{%- endif %}
|
6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
7 |
+
{%- for tool in tools %}
|
8 |
+
{{- "\n" }}
|
9 |
+
{{- tool | tojson }}
|
10 |
+
{%- endfor %}
|
11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
12 |
+
{%- else %}
|
13 |
+
{%- if messages[0].role == 'system' %}
|
14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
15 |
+
{%- endif %}
|
16 |
+
{%- endif %}
|
17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
18 |
+
{%- for message in messages[::-1] %}
|
19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
21 |
+
{%- set ns.multi_step_tool = false %}
|
22 |
+
{%- set ns.last_query_index = index %}
|
23 |
+
{%- endif %}
|
24 |
+
{%- endfor %}
|
25 |
+
{%- for message in messages %}
|
26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
28 |
+
{%- elif message.role == "assistant" %}
|
29 |
+
{%- set content = message.content %}
|
30 |
+
{%- set reasoning_content = '' %}
|
31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
33 |
+
{%- else %}
|
34 |
+
{%- if '</think>' in message.content %}
|
35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
37 |
+
{%- endif %}
|
38 |
+
{%- endif %}
|
39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
42 |
+
{%- else %}
|
43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
44 |
+
{%- endif %}
|
45 |
+
{%- else %}
|
46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
47 |
+
{%- endif %}
|
48 |
+
{%- if message.tool_calls %}
|
49 |
+
{%- for tool_call in message.tool_calls %}
|
50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
51 |
+
{{- '\n' }}
|
52 |
+
{%- endif %}
|
53 |
+
{%- if tool_call.function %}
|
54 |
+
{%- set tool_call = tool_call.function %}
|
55 |
+
{%- endif %}
|
56 |
+
{{- '<tool_call>\n{"name": "' }}
|
57 |
+
{{- tool_call.name }}
|
58 |
+
{{- '", "arguments": ' }}
|
59 |
+
{%- if tool_call.arguments is string %}
|
60 |
+
{{- tool_call.arguments }}
|
61 |
+
{%- else %}
|
62 |
+
{{- tool_call.arguments | tojson }}
|
63 |
+
{%- endif %}
|
64 |
+
{{- '}\n</tool_call>' }}
|
65 |
+
{%- endfor %}
|
66 |
+
{%- endif %}
|
67 |
+
{{- '<|im_end|>\n' }}
|
68 |
+
{%- elif message.role == "tool" %}
|
69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
70 |
+
{{- '<|im_start|>user' }}
|
71 |
+
{%- endif %}
|
72 |
+
{{- '\n<tool_response>\n' }}
|
73 |
+
{{- message.content }}
|
74 |
+
{{- '\n</tool_response>' }}
|
75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
76 |
+
{{- '<|im_end|>\n' }}
|
77 |
+
{%- endif %}
|
78 |
+
{%- endif %}
|
79 |
+
{%- endfor %}
|
80 |
+
{%- if add_generation_prompt %}
|
81 |
+
{{- '<|im_start|>assistant\n' }}
|
82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
84 |
+
{%- endif %}
|
85 |
+
{%- endif %}
|
config.json
CHANGED
@@ -4,7 +4,6 @@
|
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 151643,
|
8 |
"decoder_sparse_step": 1,
|
9 |
"eos_token_id": 151645,
|
10 |
"head_dim": 128,
|
@@ -24,6 +23,7 @@
|
|
24 |
"num_hidden_layers": 48,
|
25 |
"num_key_value_heads": 4,
|
26 |
"output_router_logits": false,
|
|
|
27 |
"rms_norm_eps": 1e-06,
|
28 |
"rope_scaling": null,
|
29 |
"rope_theta": 1000000.0,
|
@@ -31,8 +31,9 @@
|
|
31 |
"sliding_window": null,
|
32 |
"tie_word_embeddings": false,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
-
"transformers_version": "4.
|
|
|
35 |
"use_cache": true,
|
36 |
"use_sliding_window": false,
|
37 |
"vocab_size": 151936
|
38 |
-
}
|
|
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
|
|
7 |
"decoder_sparse_step": 1,
|
8 |
"eos_token_id": 151645,
|
9 |
"head_dim": 128,
|
|
|
23 |
"num_hidden_layers": 48,
|
24 |
"num_key_value_heads": 4,
|
25 |
"output_router_logits": false,
|
26 |
+
"pad_token_id": 151654,
|
27 |
"rms_norm_eps": 1e-06,
|
28 |
"rope_scaling": null,
|
29 |
"rope_theta": 1000000.0,
|
|
|
31 |
"sliding_window": null,
|
32 |
"tie_word_embeddings": false,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.52.0.dev0",
|
35 |
+
"unsloth_fixed": true,
|
36 |
"use_cache": true,
|
37 |
"use_sliding_window": false,
|
38 |
"vocab_size": 151936
|
39 |
+
}
|
generation_config.json
CHANGED
@@ -1,13 +1,14 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
|
|
|
1 |
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"max_length": 40960,
|
9 |
+
"pad_token_id": 151654,
|
10 |
+
"temperature": 0.6,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.95,
|
13 |
+
"transformers_version": "4.52.0.dev0"
|
14 |
+
}
|
model-00001-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e80e793f3403fbc12b7360cea3b7488dd9e13bcfe53732e0d2f85700ab6a344
|
3 |
+
size 4997184968
|
model-00002-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50754c62e928b29e2eaa2ade1e61624b27d24877ca37eda85a51de8a3e74e469
|
3 |
+
size 4997741608
|
model-00003-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26dea45e135f339e82140cfa1e7c06a8888873a36ef78405df92a5af3fd29695
|
3 |
+
size 4997742208
|
model-00004-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4b69db4edcad5460dfd30dbcce27478aeccb37d58c59ed58f7bb91cb5062c69
|
3 |
+
size 4997743184
|
model-00005-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23cf0c76fe660de4143e0c9865c5ec98aa4d5d57298f89a831ceaa08a3def7b7
|
3 |
+
size 4997743184
|
model-00006-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb7cf589b67bac2cb47e9fb836bf55272aa694528447c5993c1b37c0df0d648
|
3 |
+
size 4997743184
|
model-00007-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d561d6abce11ff85a914ea00e3c8befada0070325a8e5c01d935fea0b85aafe1
|
3 |
+
size 4997743184
|
model-00008-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a3828fb7caa650fb58ada0d94702c4d54d8f120002d9d86926f4b82608ff249
|
3 |
+
size 4997743184
|
model-00009-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732a117f266a266432e19fdb4e3d1a1b77965b90be98e3c4e4d054b94727944f
|
3 |
+
size 4997743184
|
model-00010-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed69f078d52a6cef3075d7b4c9547a0abcd62b1483a55d7711a594f7bb7ebefa
|
3 |
+
size 4997743184
|
model-00011-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:625947b70501b3f3e45c4196ef37947cbdde01fd2d4d5009be14173362125314
|
3 |
+
size 4997743184
|
model-00012-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08bf9d9d3eb50aebd667033a2d18bde73f0558c1552e92a1ed77a8563279fafa
|
3 |
+
size 4997743184
|
model-00013-of-00013.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c8b6778746d3bea52fe78db8e7709d277e80ea48e1c8fe8940d928e6b7168b4
|
3 |
+
size 1094220288
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"single_word": false
|
23 |
},
|
24 |
"pad_token": {
|
25 |
-
"content": "<|
|
26 |
"lstrip": false,
|
27 |
"normalized": false,
|
28 |
"rstrip": false,
|
|
|
22 |
"single_word": false
|
23 |
},
|
24 |
"pad_token": {
|
25 |
+
"content": "<|vision_pad|>",
|
26 |
"lstrip": false,
|
27 |
"normalized": false,
|
28 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -227,13 +227,15 @@
|
|
227 |
"<|video_pad|>"
|
228 |
],
|
229 |
"bos_token": null,
|
230 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
231 |
"clean_up_tokenization_spaces": false,
|
232 |
"eos_token": "<|im_end|>",
|
233 |
"errors": "replace",
|
234 |
-
"
|
235 |
-
"
|
|
|
|
|
236 |
"split_special_tokens": false,
|
237 |
"tokenizer_class": "Qwen2Tokenizer",
|
238 |
-
"unk_token": null
|
|
|
239 |
}
|
|
|
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": 40960,
|
235 |
+
"pad_token": "<|vision_pad|>",
|
236 |
+
"padding_side": "left",
|
237 |
"split_special_tokens": false,
|
238 |
"tokenizer_class": "Qwen2Tokenizer",
|
239 |
+
"unk_token": null,
|
240 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}"
|
241 |
}
|