Hugging Face's logo

Qwen
/
Qwen3-30B-A3B-Thinking-2507-FP8

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
fp8
Model card Files
xet
Community
1
littlebird13 commited on
Commit
2ed5e4c
·
verified ·
1 Parent(s): cfa4ca2

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +194 -0
  3. generation_config.json +13 -0
  4. merges.txt +0 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +240 -0
  12. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
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,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 262144,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
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": 10000000,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.51.0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936,
38
+ "quantization_config": {
39
+ "activation_scheme": "dynamic",
40
+ "modules_to_not_convert": [
41
+ "lm_head",
42
+ "model.layers.0.input_layernorm",
43
+ "model.layers.0.mlp.gate",
44
+ "model.layers.0.post_attention_layernorm",
45
+ "model.layers.1.input_layernorm",
46
+ "model.layers.1.mlp.gate",
47
+ "model.layers.1.post_attention_layernorm",
48
+ "model.layers.2.input_layernorm",
49
+ "model.layers.2.mlp.gate",
50
+ "model.layers.2.post_attention_layernorm",
51
+ "model.layers.3.input_layernorm",
52
+ "model.layers.3.mlp.gate",
53
+ "model.layers.3.post_attention_layernorm",
54
+ "model.layers.4.input_layernorm",
55
+ "model.layers.4.mlp.gate",
56
+ "model.layers.4.post_attention_layernorm",
57
+ "model.layers.5.input_layernorm",
58
+ "model.layers.5.mlp.gate",
59
+ "model.layers.5.post_attention_layernorm",
60
+ "model.layers.6.input_layernorm",
61
+ "model.layers.6.mlp.gate",
62
+ "model.layers.6.post_attention_layernorm",
63
+ "model.layers.7.input_layernorm",
64
+ "model.layers.7.mlp.gate",
65
+ "model.layers.7.post_attention_layernorm",
66
+ "model.layers.8.input_layernorm",
67
+ "model.layers.8.mlp.gate",
68
+ "model.layers.8.post_attention_layernorm",
69
+ "model.layers.9.input_layernorm",
70
+ "model.layers.9.mlp.gate",
71
+ "model.layers.9.post_attention_layernorm",
72
+ "model.layers.10.input_layernorm",
73
+ "model.layers.10.mlp.gate",
74
+ "model.layers.10.post_attention_layernorm",
75
+ "model.layers.11.input_layernorm",
76
+ "model.layers.11.mlp.gate",
77
+ "model.layers.11.post_attention_layernorm",
78
+ "model.layers.12.input_layernorm",
79
+ "model.layers.12.mlp.gate",
80
+ "model.layers.12.post_attention_layernorm",
81
+ "model.layers.13.input_layernorm",
82
+ "model.layers.13.mlp.gate",
83
+ "model.layers.13.post_attention_layernorm",
84
+ "model.layers.14.input_layernorm",
85
+ "model.layers.14.mlp.gate",
86
+ "model.layers.14.post_attention_layernorm",
87
+ "model.layers.15.input_layernorm",
88
+ "model.layers.15.mlp.gate",
89
+ "model.layers.15.post_attention_layernorm",
90
+ "model.layers.16.input_layernorm",
91
+ "model.layers.16.mlp.gate",
92
+ "model.layers.16.post_attention_layernorm",
93
+ "model.layers.17.input_layernorm",
94
+ "model.layers.17.mlp.gate",
95
+ "model.layers.17.post_attention_layernorm",
96
+ "model.layers.18.input_layernorm",
97
+ "model.layers.18.mlp.gate",
98
+ "model.layers.18.post_attention_layernorm",
99
+ "model.layers.19.input_layernorm",
100
+ "model.layers.19.mlp.gate",
101
+ "model.layers.19.post_attention_layernorm",
102
+ "model.layers.20.input_layernorm",
103
+ "model.layers.20.mlp.gate",
104
+ "model.layers.20.post_attention_layernorm",
105
+ "model.layers.21.input_layernorm",
106
+ "model.layers.21.mlp.gate",
107
+ "model.layers.21.post_attention_layernorm",
108
+ "model.layers.22.input_layernorm",
109
+ "model.layers.22.mlp.gate",
110
+ "model.layers.22.post_attention_layernorm",
111
+ "model.layers.23.input_layernorm",
112
+ "model.layers.23.mlp.gate",
113
+ "model.layers.23.post_attention_layernorm",
114
+ "model.layers.24.input_layernorm",
115
+ "model.layers.24.mlp.gate",
116
+ "model.layers.24.post_attention_layernorm",
117
+ "model.layers.25.input_layernorm",
118
+ "model.layers.25.mlp.gate",
119
+ "model.layers.25.post_attention_layernorm",
120
+ "model.layers.26.input_layernorm",
121
+ "model.layers.26.mlp.gate",
122
+ "model.layers.26.post_attention_layernorm",
123
+ "model.layers.27.input_layernorm",
124
+ "model.layers.27.mlp.gate",
125
+ "model.layers.27.post_attention_layernorm",
126
+ "model.layers.28.input_layernorm",
127
+ "model.layers.28.mlp.gate",
128
+ "model.layers.28.post_attention_layernorm",
129
+ "model.layers.29.input_layernorm",
130
+ "model.layers.29.mlp.gate",
131
+ "model.layers.29.post_attention_layernorm",
132
+ "model.layers.30.input_layernorm",
133
+ "model.layers.30.mlp.gate",
134
+ "model.layers.30.post_attention_layernorm",
135
+ "model.layers.31.input_layernorm",
136
+ "model.layers.31.mlp.gate",
137
+ "model.layers.31.post_attention_layernorm",
138
+ "model.layers.32.input_layernorm",
139
+ "model.layers.32.mlp.gate",
140
+ "model.layers.32.post_attention_layernorm",
141
+ "model.layers.33.input_layernorm",
142
+ "model.layers.33.mlp.gate",
143
+ "model.layers.33.post_attention_layernorm",
144
+ "model.layers.34.input_layernorm",
145
+ "model.layers.34.mlp.gate",
146
+ "model.layers.34.post_attention_layernorm",
147
+ "model.layers.35.input_layernorm",
148
+ "model.layers.35.mlp.gate",
149
+ "model.layers.35.post_attention_layernorm",
150
+ "model.layers.36.input_layernorm",
151
+ "model.layers.36.mlp.gate",
152
+ "model.layers.36.post_attention_layernorm",
153
+ "model.layers.37.input_layernorm",
154
+ "model.layers.37.mlp.gate",
155
+ "model.layers.37.post_attention_layernorm",
156
+ "model.layers.38.input_layernorm",
157
+ "model.layers.38.mlp.gate",
158
+ "model.layers.38.post_attention_layernorm",
159
+ "model.layers.39.input_layernorm",
160
+ "model.layers.39.mlp.gate",
161
+ "model.layers.39.post_attention_layernorm",
162
+ "model.layers.40.input_layernorm",
163
+ "model.layers.40.mlp.gate",
164
+ "model.layers.40.post_attention_layernorm",
165
+ "model.layers.41.input_layernorm",
166
+ "model.layers.41.mlp.gate",
167
+ "model.layers.41.post_attention_layernorm",
168
+ "model.layers.42.input_layernorm",
169
+ "model.layers.42.mlp.gate",
170
+ "model.layers.42.post_attention_layernorm",
171
+ "model.layers.43.input_layernorm",
172
+ "model.layers.43.mlp.gate",
173
+ "model.layers.43.post_attention_layernorm",
174
+ "model.layers.44.input_layernorm",
175
+ "model.layers.44.mlp.gate",
176
+ "model.layers.44.post_attention_layernorm",
177
+ "model.layers.45.input_layernorm",
178
+ "model.layers.45.mlp.gate",
179
+ "model.layers.45.post_attention_layernorm",
180
+ "model.layers.46.input_layernorm",
181
+ "model.layers.46.mlp.gate",
182
+ "model.layers.46.post_attention_layernorm",
183
+ "model.layers.47.input_layernorm",
184
+ "model.layers.47.mlp.gate",
185
+ "model.layers.47.post_attention_layernorm"
186
+ ],
187
+ "fmt": "e4m3",
188
+ "quant_method": "fp8",
189
+ "weight_block_size": [
190
+ 128,
191
+ 128
192
+ ]
193
+ }
194
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a85269b0d624ed844845ea3e03013dfd1691995dbc8fa46e815256465cee8f
3
+ size 10001462368
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60430cdea27d52cf26dee8e1da8831da29945d07b2a95858a62589045cb2923
3
+ size 10000577408
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8508cdfd010f9f440a55fa9fb49b6d6d007c2b869dc828c0fdf326fab7108b98
3
+ size 10000577448
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b2f0410e9f6d807c336616ba3dd308ce6e87591e22aed408bf85b7029f3360
3
+ size 1173001360
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "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 message.content is string 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.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.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 {{- 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
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff