littlebird13 commited on
Commit
d29dc93
·
verified ·
1 Parent(s): eea830f

Add files using upload-large-folder tool

Browse files
.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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,334 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 10944,
15
+ "max_position_embeddings": 1048576,
16
+ "max_window_layers": 28,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 1536,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 64,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 94,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "qkv_bias": false,
28
+ "quantization_config": {
29
+ "activation_scheme": "dynamic",
30
+ "modules_to_not_convert": [
31
+ "lm_head",
32
+ "model.layers.0.input_layernorm",
33
+ "model.layers.0.mlp.gate",
34
+ "model.layers.0.post_attention_layernorm",
35
+ "model.layers.1.input_layernorm",
36
+ "model.layers.1.mlp.gate",
37
+ "model.layers.1.post_attention_layernorm",
38
+ "model.layers.2.input_layernorm",
39
+ "model.layers.2.mlp.gate",
40
+ "model.layers.2.post_attention_layernorm",
41
+ "model.layers.3.input_layernorm",
42
+ "model.layers.3.mlp.gate",
43
+ "model.layers.3.post_attention_layernorm",
44
+ "model.layers.4.input_layernorm",
45
+ "model.layers.4.mlp.gate",
46
+ "model.layers.4.post_attention_layernorm",
47
+ "model.layers.5.input_layernorm",
48
+ "model.layers.5.mlp.gate",
49
+ "model.layers.5.post_attention_layernorm",
50
+ "model.layers.6.input_layernorm",
51
+ "model.layers.6.mlp.gate",
52
+ "model.layers.6.post_attention_layernorm",
53
+ "model.layers.7.input_layernorm",
54
+ "model.layers.7.mlp.gate",
55
+ "model.layers.7.post_attention_layernorm",
56
+ "model.layers.8.input_layernorm",
57
+ "model.layers.8.mlp.gate",
58
+ "model.layers.8.post_attention_layernorm",
59
+ "model.layers.9.input_layernorm",
60
+ "model.layers.9.mlp.gate",
61
+ "model.layers.9.post_attention_layernorm",
62
+ "model.layers.10.input_layernorm",
63
+ "model.layers.10.mlp.gate",
64
+ "model.layers.10.post_attention_layernorm",
65
+ "model.layers.11.input_layernorm",
66
+ "model.layers.11.mlp.gate",
67
+ "model.layers.11.post_attention_layernorm",
68
+ "model.layers.12.input_layernorm",
69
+ "model.layers.12.mlp.gate",
70
+ "model.layers.12.post_attention_layernorm",
71
+ "model.layers.13.input_layernorm",
72
+ "model.layers.13.mlp.gate",
73
+ "model.layers.13.post_attention_layernorm",
74
+ "model.layers.14.input_layernorm",
75
+ "model.layers.14.mlp.gate",
76
+ "model.layers.14.post_attention_layernorm",
77
+ "model.layers.15.input_layernorm",
78
+ "model.layers.15.mlp.gate",
79
+ "model.layers.15.post_attention_layernorm",
80
+ "model.layers.16.input_layernorm",
81
+ "model.layers.16.mlp.gate",
82
+ "model.layers.16.post_attention_layernorm",
83
+ "model.layers.17.input_layernorm",
84
+ "model.layers.17.mlp.gate",
85
+ "model.layers.17.post_attention_layernorm",
86
+ "model.layers.18.input_layernorm",
87
+ "model.layers.18.mlp.gate",
88
+ "model.layers.18.post_attention_layernorm",
89
+ "model.layers.19.input_layernorm",
90
+ "model.layers.19.mlp.gate",
91
+ "model.layers.19.post_attention_layernorm",
92
+ "model.layers.20.input_layernorm",
93
+ "model.layers.20.mlp.gate",
94
+ "model.layers.20.post_attention_layernorm",
95
+ "model.layers.21.input_layernorm",
96
+ "model.layers.21.mlp.gate",
97
+ "model.layers.21.post_attention_layernorm",
98
+ "model.layers.22.input_layernorm",
99
+ "model.layers.22.mlp.gate",
100
+ "model.layers.22.post_attention_layernorm",
101
+ "model.layers.23.input_layernorm",
102
+ "model.layers.23.mlp.gate",
103
+ "model.layers.23.post_attention_layernorm",
104
+ "model.layers.24.input_layernorm",
105
+ "model.layers.24.mlp.gate",
106
+ "model.layers.24.post_attention_layernorm",
107
+ "model.layers.25.input_layernorm",
108
+ "model.layers.25.mlp.gate",
109
+ "model.layers.25.post_attention_layernorm",
110
+ "model.layers.26.input_layernorm",
111
+ "model.layers.26.mlp.gate",
112
+ "model.layers.26.post_attention_layernorm",
113
+ "model.layers.27.input_layernorm",
114
+ "model.layers.27.mlp.gate",
115
+ "model.layers.27.post_attention_layernorm",
116
+ "model.layers.28.input_layernorm",
117
+ "model.layers.28.mlp.gate",
118
+ "model.layers.28.post_attention_layernorm",
119
+ "model.layers.29.input_layernorm",
120
+ "model.layers.29.mlp.gate",
121
+ "model.layers.29.post_attention_layernorm",
122
+ "model.layers.30.input_layernorm",
123
+ "model.layers.30.mlp.gate",
124
+ "model.layers.30.post_attention_layernorm",
125
+ "model.layers.31.input_layernorm",
126
+ "model.layers.31.mlp.gate",
127
+ "model.layers.31.post_attention_layernorm",
128
+ "model.layers.32.input_layernorm",
129
+ "model.layers.32.mlp.gate",
130
+ "model.layers.32.post_attention_layernorm",
131
+ "model.layers.33.input_layernorm",
132
+ "model.layers.33.mlp.gate",
133
+ "model.layers.33.post_attention_layernorm",
134
+ "model.layers.34.input_layernorm",
135
+ "model.layers.34.mlp.gate",
136
+ "model.layers.34.post_attention_layernorm",
137
+ "model.layers.35.input_layernorm",
138
+ "model.layers.35.mlp.gate",
139
+ "model.layers.35.post_attention_layernorm",
140
+ "model.layers.36.input_layernorm",
141
+ "model.layers.36.mlp.gate",
142
+ "model.layers.36.post_attention_layernorm",
143
+ "model.layers.37.input_layernorm",
144
+ "model.layers.37.mlp.gate",
145
+ "model.layers.37.post_attention_layernorm",
146
+ "model.layers.38.input_layernorm",
147
+ "model.layers.38.mlp.gate",
148
+ "model.layers.38.post_attention_layernorm",
149
+ "model.layers.39.input_layernorm",
150
+ "model.layers.39.mlp.gate",
151
+ "model.layers.39.post_attention_layernorm",
152
+ "model.layers.40.input_layernorm",
153
+ "model.layers.40.mlp.gate",
154
+ "model.layers.40.post_attention_layernorm",
155
+ "model.layers.41.input_layernorm",
156
+ "model.layers.41.mlp.gate",
157
+ "model.layers.41.post_attention_layernorm",
158
+ "model.layers.42.input_layernorm",
159
+ "model.layers.42.mlp.gate",
160
+ "model.layers.42.post_attention_layernorm",
161
+ "model.layers.43.input_layernorm",
162
+ "model.layers.43.mlp.gate",
163
+ "model.layers.43.post_attention_layernorm",
164
+ "model.layers.44.input_layernorm",
165
+ "model.layers.44.mlp.gate",
166
+ "model.layers.44.post_attention_layernorm",
167
+ "model.layers.45.input_layernorm",
168
+ "model.layers.45.mlp.gate",
169
+ "model.layers.45.post_attention_layernorm",
170
+ "model.layers.46.input_layernorm",
171
+ "model.layers.46.mlp.gate",
172
+ "model.layers.46.post_attention_layernorm",
173
+ "model.layers.47.input_layernorm",
174
+ "model.layers.47.mlp.gate",
175
+ "model.layers.47.post_attention_layernorm",
176
+ "model.layers.48.input_layernorm",
177
+ "model.layers.48.mlp.gate",
178
+ "model.layers.48.post_attention_layernorm",
179
+ "model.layers.49.input_layernorm",
180
+ "model.layers.49.mlp.gate",
181
+ "model.layers.49.post_attention_layernorm",
182
+ "model.layers.50.input_layernorm",
183
+ "model.layers.50.mlp.gate",
184
+ "model.layers.50.post_attention_layernorm",
185
+ "model.layers.51.input_layernorm",
186
+ "model.layers.51.mlp.gate",
187
+ "model.layers.51.post_attention_layernorm",
188
+ "model.layers.52.input_layernorm",
189
+ "model.layers.52.mlp.gate",
190
+ "model.layers.52.post_attention_layernorm",
191
+ "model.layers.53.input_layernorm",
192
+ "model.layers.53.mlp.gate",
193
+ "model.layers.53.post_attention_layernorm",
194
+ "model.layers.54.input_layernorm",
195
+ "model.layers.54.mlp.gate",
196
+ "model.layers.54.post_attention_layernorm",
197
+ "model.layers.55.input_layernorm",
198
+ "model.layers.55.mlp.gate",
199
+ "model.layers.55.post_attention_layernorm",
200
+ "model.layers.56.input_layernorm",
201
+ "model.layers.56.mlp.gate",
202
+ "model.layers.56.post_attention_layernorm",
203
+ "model.layers.57.input_layernorm",
204
+ "model.layers.57.mlp.gate",
205
+ "model.layers.57.post_attention_layernorm",
206
+ "model.layers.58.input_layernorm",
207
+ "model.layers.58.mlp.gate",
208
+ "model.layers.58.post_attention_layernorm",
209
+ "model.layers.59.input_layernorm",
210
+ "model.layers.59.mlp.gate",
211
+ "model.layers.59.post_attention_layernorm",
212
+ "model.layers.60.input_layernorm",
213
+ "model.layers.60.mlp.gate",
214
+ "model.layers.60.post_attention_layernorm",
215
+ "model.layers.61.input_layernorm",
216
+ "model.layers.61.mlp.gate",
217
+ "model.layers.61.post_attention_layernorm",
218
+ "model.layers.62.input_layernorm",
219
+ "model.layers.62.mlp.gate",
220
+ "model.layers.62.post_attention_layernorm",
221
+ "model.layers.63.input_layernorm",
222
+ "model.layers.63.mlp.gate",
223
+ "model.layers.63.post_attention_layernorm",
224
+ "model.layers.64.input_layernorm",
225
+ "model.layers.64.mlp.gate",
226
+ "model.layers.64.post_attention_layernorm",
227
+ "model.layers.65.input_layernorm",
228
+ "model.layers.65.mlp.gate",
229
+ "model.layers.65.post_attention_layernorm",
230
+ "model.layers.66.input_layernorm",
231
+ "model.layers.66.mlp.gate",
232
+ "model.layers.66.post_attention_layernorm",
233
+ "model.layers.67.input_layernorm",
234
+ "model.layers.67.mlp.gate",
235
+ "model.layers.67.post_attention_layernorm",
236
+ "model.layers.68.input_layernorm",
237
+ "model.layers.68.mlp.gate",
238
+ "model.layers.68.post_attention_layernorm",
239
+ "model.layers.69.input_layernorm",
240
+ "model.layers.69.mlp.gate",
241
+ "model.layers.69.post_attention_layernorm",
242
+ "model.layers.70.input_layernorm",
243
+ "model.layers.70.mlp.gate",
244
+ "model.layers.70.post_attention_layernorm",
245
+ "model.layers.71.input_layernorm",
246
+ "model.layers.71.mlp.gate",
247
+ "model.layers.71.post_attention_layernorm",
248
+ "model.layers.72.input_layernorm",
249
+ "model.layers.72.mlp.gate",
250
+ "model.layers.72.post_attention_layernorm",
251
+ "model.layers.73.input_layernorm",
252
+ "model.layers.73.mlp.gate",
253
+ "model.layers.73.post_attention_layernorm",
254
+ "model.layers.74.input_layernorm",
255
+ "model.layers.74.mlp.gate",
256
+ "model.layers.74.post_attention_layernorm",
257
+ "model.layers.75.input_layernorm",
258
+ "model.layers.75.mlp.gate",
259
+ "model.layers.75.post_attention_layernorm",
260
+ "model.layers.76.input_layernorm",
261
+ "model.layers.76.mlp.gate",
262
+ "model.layers.76.post_attention_layernorm",
263
+ "model.layers.77.input_layernorm",
264
+ "model.layers.77.mlp.gate",
265
+ "model.layers.77.post_attention_layernorm",
266
+ "model.layers.78.input_layernorm",
267
+ "model.layers.78.mlp.gate",
268
+ "model.layers.78.post_attention_layernorm",
269
+ "model.layers.79.input_layernorm",
270
+ "model.layers.79.mlp.gate",
271
+ "model.layers.79.post_attention_layernorm",
272
+ "model.layers.80.input_layernorm",
273
+ "model.layers.80.mlp.gate",
274
+ "model.layers.80.post_attention_layernorm",
275
+ "model.layers.81.input_layernorm",
276
+ "model.layers.81.mlp.gate",
277
+ "model.layers.81.post_attention_layernorm",
278
+ "model.layers.82.input_layernorm",
279
+ "model.layers.82.mlp.gate",
280
+ "model.layers.82.post_attention_layernorm",
281
+ "model.layers.83.input_layernorm",
282
+ "model.layers.83.mlp.gate",
283
+ "model.layers.83.post_attention_layernorm",
284
+ "model.layers.84.input_layernorm",
285
+ "model.layers.84.mlp.gate",
286
+ "model.layers.84.post_attention_layernorm",
287
+ "model.layers.85.input_layernorm",
288
+ "model.layers.85.mlp.gate",
289
+ "model.layers.85.post_attention_layernorm",
290
+ "model.layers.86.input_layernorm",
291
+ "model.layers.86.mlp.gate",
292
+ "model.layers.86.post_attention_layernorm",
293
+ "model.layers.87.input_layernorm",
294
+ "model.layers.87.mlp.gate",
295
+ "model.layers.87.post_attention_layernorm",
296
+ "model.layers.88.input_layernorm",
297
+ "model.layers.88.mlp.gate",
298
+ "model.layers.88.post_attention_layernorm",
299
+ "model.layers.89.input_layernorm",
300
+ "model.layers.89.mlp.gate",
301
+ "model.layers.89.post_attention_layernorm",
302
+ "model.layers.90.input_layernorm",
303
+ "model.layers.90.mlp.gate",
304
+ "model.layers.90.post_attention_layernorm",
305
+ "model.layers.91.input_layernorm",
306
+ "model.layers.91.mlp.gate",
307
+ "model.layers.91.post_attention_layernorm",
308
+ "model.layers.92.input_layernorm",
309
+ "model.layers.92.mlp.gate",
310
+ "model.layers.92.post_attention_layernorm",
311
+ "model.layers.93.input_layernorm",
312
+ "model.layers.93.mlp.gate",
313
+ "model.layers.93.post_attention_layernorm"
314
+ ],
315
+ "quant_method": "fp8",
316
+ "weight_block_size": [
317
+ 128,
318
+ 128
319
+ ]
320
+ },
321
+ "rms_norm_eps": 1e-06,
322
+ "rope_scaling": null,
323
+ "rope_theta": 5000000,
324
+ "router_aux_loss_coef": 0.0,
325
+ "shared_expert_intermediate_size": 0,
326
+ "sliding_window": null,
327
+ "tie_word_embeddings": false,
328
+ "torch_dtype": "bfloat16",
329
+ "transformers_version": "4.51.3",
330
+ "use_cache": true,
331
+ "use_qk_norm": true,
332
+ "use_sliding_window": false,
333
+ "vocab_size": 151936
334
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84f30f1914682a6f15e144cae333e309bd777da10202592e565c0d675ec2b76
3
+ size 9997546840
model-00002-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65469ac9af3b91abc9261ff69ece4f74cdf736c2f54ebaccfd552f466e405777
3
+ size 9998803944
model-00003-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9015279416f042af0bf29fb69f9f63d12f74988f76704ddf108ca075b52ae46
3
+ size 9998805544
model-00004-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760c68ecd1489adef0f68a41f9635ac8d7ae1a17aa65b91ad8aaa843cc5714a2
3
+ size 9998807112
model-00005-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3865d386da838f0ca3b739cdd9838dbeb792d7f8512cc2ecddee111a20ea42c5
3
+ size 9998807128
model-00006-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d98e002bd1f5a92d8d60ea9ebf69a4b008125e649ea1b2650931357fb68698a
3
+ size 9998807144
model-00007-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa011870767a6356ca25d70e30ab97933d67508a5afc28aa71f9ef541211a68f
3
+ size 9998807160
model-00008-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b17c05f9d0c5a4d38a6a96932189abf2355dc27cac6f64c58eb1771c2175b6b2
3
+ size 9998807168
model-00009-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3146afcfaefc235f1b71a760f843e745c0055757240bc9fc54c9eeef771080
3
+ size 9998807184
model-00010-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7253bc62c8500da2e7a0fe616a8578ebbd7c58de495ad054c8e6cf1bc90e276
3
+ size 9998807200
model-00011-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4537739a01dfb5dd0817b06189b6fd77ef62d40743660ef10dac3933842465d2
3
+ size 9998807208
model-00012-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9490c295e92ed916bf554f60c5344ad0b2a75bf95c99c6004c1d01d2ab2ab3c4
3
+ size 9998807224
model-00013-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00245ab3c6eb49692b02ae706bee8cc7c121f644dfb39033050383652ebb8be3
3
+ size 9998807248
model-00014-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218937db77e2d36abbc1fa7331f2f9b5d9ff21484ce4796de1f1f00f4b7d4108
3
+ size 9998807272
model-00015-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4bd31be54c6c4c7a2ec9d85cbf55d8b24388e24ed5998e36360bf8fae77e480
3
+ size 9998807304
model-00016-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8850d4668911d47b8edd6b1bf0c7bbf6826009a9790cb9fa301b6fd2320a2e4
3
+ size 9998807320
model-00017-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91a5a272b21e60f1a56c28f4f813d69dafdb13e7b1286921c818839b170d746
3
+ size 9998807344
model-00018-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb974ec604bc7a4346c71e87b51cdf7769e34b20c0eb194f186a86bc25338d1e
3
+ size 9998807360
model-00019-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efac9ac8685ba681e022e3905e3ca43996a925d05cf006ca14cb08fa7344bc9
3
+ size 9998807376
model-00020-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beeaff11c32b1245ed39fb5c14f8575699846ab7ca2fa9b304637757fb00ad28
3
+ size 9998807384
model-00021-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16de904a3508c24891b694ed63bf0dc9bda2576b60958cfa95d7e5ba7ba26e10
3
+ size 9998807408
model-00022-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1334f7e1f33011c006a29d594f9ab65cf0cb15325543f07e4d406c610856d5b1
3
+ size 9998807416
model-00023-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1b61799bf3bf058775940ba341eb71753f5cefc2a86323bd2c2a590010dbcd
3
+ size 9998807432
model-00024-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44ebc8e3cf519f15ee1c100f23e24c1ac239b84e49fbf7503de638e09d27bc4
3
+ size 6454892160
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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