JunHowie commited on
Commit
bb44350
·
verified ·
1 Parent(s): 3d41990

Upload folder using huggingface_hub

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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "quantization_config": {
21
+ "bits": 8,
22
+ "checkpoint_format": "gptq",
23
+ "desc_act": true,
24
+ "group_size": 128,
25
+ "lm_head": false,
26
+ "meta": {
27
+ "damp_auto_increment": 0.0025,
28
+ "damp_percent": 0.01,
29
+ "mse": 0.0,
30
+ "quantizer": [
31
+ "gptqmodel:2.2.0"
32
+ ],
33
+ "static_groups": false,
34
+ "true_sequential": true,
35
+ "uri": "https://github.com/modelcloud/gptqmodel"
36
+ },
37
+ "pack_dtype": "int32",
38
+ "quant_method": "gptq",
39
+ "sym": true
40
+ },
41
+ "rms_norm_eps": 1e-06,
42
+ "rope_scaling": null,
43
+ "rope_theta": 1000000,
44
+ "sliding_window": null,
45
+ "tie_word_embeddings": true,
46
+ "torch_dtype": "bfloat16",
47
+ "transformers_version": "4.51.3",
48
+ "use_cache": true,
49
+ "use_sliding_window": false,
50
+ "vocab_size": 151936
51
+ }
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": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08d7f602c69d9a6b307c9443ea4e02a78a872950bfb10cc71361da5e13bcc34
3
+ size 763265408
quant_log.csv ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.00034001,0.01000,0.702
3
+ 0,self_attn.v_proj,0.00026275,0.01000,0.516
4
+ 0,self_attn.q_proj,0.00078015,0.01000,0.472
5
+ 0,self_attn.o_proj,0.00021305,0.01000,0.944
6
+ 0,mlp.up_proj,0.00412678,0.01000,0.466
7
+ 0,mlp.gate_proj,0.00822148,0.01000,0.479
8
+ 0,mlp.down_proj,0.00023430,0.01000,1.461
9
+ 1,self_attn.k_proj,0.00014082,0.01000,0.490
10
+ 1,self_attn.v_proj,0.00013241,0.01000,0.586
11
+ 1,self_attn.q_proj,0.00031780,0.01000,0.512
12
+ 1,self_attn.o_proj,0.00004038,0.01000,1.020
13
+ 1,mlp.up_proj,0.01444682,0.01000,0.496
14
+ 1,mlp.gate_proj,0.04915192,0.01000,0.495
15
+ 1,mlp.down_proj,0.00029908,0.01000,1.443
16
+ 2,self_attn.k_proj,0.00026053,0.01000,0.468
17
+ 2,self_attn.v_proj,0.00024813,0.01000,0.477
18
+ 2,self_attn.q_proj,0.00060980,0.01000,0.515
19
+ 2,self_attn.o_proj,0.00006841,0.01000,1.000
20
+ 2,mlp.up_proj,0.01214469,0.01000,0.488
21
+ 2,mlp.gate_proj,0.03373746,0.01000,0.526
22
+ 2,mlp.down_proj,0.01297616,0.01000,1.444
23
+ 3,self_attn.k_proj,0.00230989,0.01000,0.465
24
+ 3,self_attn.v_proj,0.00233178,0.01000,0.470
25
+ 3,self_attn.q_proj,0.00470302,0.01000,0.480
26
+ 3,self_attn.o_proj,0.00012092,0.01000,1.027
27
+ 3,mlp.up_proj,0.01660008,0.01000,0.603
28
+ 3,mlp.gate_proj,0.04289370,0.01000,0.484
29
+ 3,mlp.down_proj,0.00092249,0.01000,1.553
30
+ 4,self_attn.k_proj,0.00206668,0.01000,0.468
31
+ 4,self_attn.v_proj,0.00214147,0.01000,0.476
32
+ 4,self_attn.q_proj,0.00418732,0.01000,-1.693
33
+ 4,self_attn.o_proj,0.00030304,0.01000,0.958
34
+ 4,mlp.up_proj,0.01767924,0.01000,0.577
35
+ 4,mlp.gate_proj,0.04030780,0.01000,0.628
36
+ 4,mlp.down_proj,0.00111819,0.01000,1.658
37
+ 5,self_attn.k_proj,0.00309932,0.01000,0.472
38
+ 5,self_attn.v_proj,0.00331202,0.01000,0.475
39
+ 5,self_attn.q_proj,0.00744162,0.01000,0.474
40
+ 5,self_attn.o_proj,0.00036463,0.01000,0.938
41
+ 5,mlp.up_proj,0.01660982,0.01000,0.518
42
+ 5,mlp.gate_proj,0.02776664,0.01000,0.543
43
+ 5,mlp.down_proj,0.00127475,0.01000,1.419
44
+ 6,self_attn.k_proj,0.00246792,0.01000,0.541
45
+ 6,self_attn.v_proj,0.00227531,0.01000,0.496
46
+ 6,self_attn.q_proj,0.00543098,0.01000,0.474
47
+ 6,self_attn.o_proj,0.00031531,0.01000,0.913
48
+ 6,mlp.up_proj,0.02119459,0.01000,0.491
49
+ 6,mlp.gate_proj,0.03364027,0.01000,0.556
50
+ 6,mlp.down_proj,0.00169318,0.01000,1.440
51
+ 7,self_attn.k_proj,0.00427833,0.01000,0.467
52
+ 7,self_attn.v_proj,0.00491385,0.01000,0.468
53
+ 7,self_attn.q_proj,0.01039105,0.01000,0.461
54
+ 7,self_attn.o_proj,0.00045247,0.01000,1.037
55
+ 7,mlp.up_proj,0.02380912,0.01000,0.474
56
+ 7,mlp.gate_proj,0.03846249,0.01000,0.477
57
+ 7,mlp.down_proj,0.00207670,0.01000,1.418
58
+ 8,self_attn.k_proj,0.00580886,0.01000,0.458
59
+ 8,self_attn.v_proj,0.00546446,0.01000,0.457
60
+ 8,self_attn.q_proj,0.01283393,0.01000,0.464
61
+ 8,self_attn.o_proj,0.00049309,0.01000,0.930
62
+ 8,mlp.up_proj,0.02529081,0.01000,0.506
63
+ 8,mlp.gate_proj,0.03940681,0.01000,0.549
64
+ 8,mlp.down_proj,0.00239061,0.01000,1.463
65
+ 9,self_attn.k_proj,0.01022408,0.01000,0.466
66
+ 9,self_attn.v_proj,0.01063569,0.01000,0.464
67
+ 9,self_attn.q_proj,0.02464896,0.01000,0.456
68
+ 9,self_attn.o_proj,0.00082228,0.01000,0.913
69
+ 9,mlp.up_proj,0.02869781,0.01000,0.475
70
+ 9,mlp.gate_proj,0.04569711,0.01000,0.495
71
+ 9,mlp.down_proj,0.00334036,0.01000,1.488
72
+ 10,self_attn.k_proj,0.00897335,0.01000,0.463
73
+ 10,self_attn.v_proj,0.00938525,0.01000,0.476
74
+ 10,self_attn.q_proj,0.02165450,0.01000,0.472
75
+ 10,self_attn.o_proj,0.00080374,0.01000,0.915
76
+ 10,mlp.up_proj,0.02908845,0.01000,0.459
77
+ 10,mlp.gate_proj,0.04619259,0.01000,0.469
78
+ 10,mlp.down_proj,0.00457235,0.01000,1.560
79
+ 11,self_attn.k_proj,0.01702636,0.01000,0.470
80
+ 11,self_attn.v_proj,0.01571462,0.01000,0.448
81
+ 11,self_attn.q_proj,0.04408321,0.01000,0.460
82
+ 11,self_attn.o_proj,0.00194463,0.01000,0.917
83
+ 11,mlp.up_proj,0.02965630,0.01000,0.471
84
+ 11,mlp.gate_proj,0.03877314,0.01000,0.465
85
+ 11,mlp.down_proj,0.00576400,0.01000,-0.688
86
+ 12,self_attn.k_proj,0.01535154,0.01000,0.461
87
+ 12,self_attn.v_proj,0.01573815,0.01000,0.463
88
+ 12,self_attn.q_proj,0.04120466,0.01000,0.464
89
+ 12,self_attn.o_proj,0.00082521,0.01000,0.993
90
+ 12,mlp.up_proj,0.02786373,0.01000,0.508
91
+ 12,mlp.gate_proj,0.03390844,0.01000,0.500
92
+ 12,mlp.down_proj,0.00530050,0.01000,1.504
93
+ 13,self_attn.k_proj,0.01469768,0.01000,0.532
94
+ 13,self_attn.v_proj,0.01746682,0.01000,0.644
95
+ 13,self_attn.q_proj,0.04317660,0.01000,0.650
96
+ 13,self_attn.o_proj,0.00115520,0.01000,0.997
97
+ 13,mlp.up_proj,0.02967896,0.01000,0.475
98
+ 13,mlp.gate_proj,0.03677811,0.01000,0.458
99
+ 13,mlp.down_proj,0.00540835,0.01000,1.386
100
+ 14,self_attn.k_proj,0.01980565,0.01000,0.452
101
+ 14,self_attn.v_proj,0.02136633,0.01000,0.458
102
+ 14,self_attn.q_proj,0.05437878,0.01000,0.463
103
+ 14,self_attn.o_proj,0.00118582,0.01000,0.909
104
+ 14,mlp.up_proj,0.03194932,0.01000,0.581
105
+ 14,mlp.gate_proj,0.03921878,0.01000,0.569
106
+ 14,mlp.down_proj,0.00719125,0.01000,1.398
107
+ 15,self_attn.k_proj,0.03463616,0.01000,0.614
108
+ 15,self_attn.v_proj,0.04363632,0.01000,0.560
109
+ 15,self_attn.q_proj,0.10855717,0.01000,0.587
110
+ 15,self_attn.o_proj,0.00174209,0.01000,1.039
111
+ 15,mlp.up_proj,0.03514949,0.01000,0.517
112
+ 15,mlp.gate_proj,0.04189382,0.01000,0.461
113
+ 15,mlp.down_proj,0.00778224,0.01000,1.585
114
+ 16,self_attn.k_proj,0.05131978,0.01000,0.457
115
+ 16,self_attn.v_proj,0.04501638,0.01000,0.453
116
+ 16,self_attn.q_proj,0.13748899,0.01000,0.460
117
+ 16,self_attn.o_proj,0.00201723,0.01000,0.920
118
+ 16,mlp.up_proj,0.04067000,0.01000,0.425
119
+ 16,mlp.gate_proj,0.04500043,0.01000,0.482
120
+ 16,mlp.down_proj,0.01533213,0.01000,-0.971
121
+ 17,self_attn.k_proj,0.10121436,0.01000,0.362
122
+ 17,self_attn.v_proj,0.12345707,0.01000,0.434
123
+ 17,self_attn.q_proj,0.30684415,0.01000,0.469
124
+ 17,self_attn.o_proj,0.00474120,0.01000,0.883
125
+ 17,mlp.up_proj,0.05722951,0.01000,0.361
126
+ 17,mlp.gate_proj,0.06477357,0.01000,0.368
127
+ 17,mlp.down_proj,0.01754329,0.01000,1.108
128
+ 18,self_attn.k_proj,0.09428492,0.01000,0.359
129
+ 18,self_attn.v_proj,0.10053023,0.01000,-1.804
130
+ 18,self_attn.q_proj,0.29437009,0.01000,0.374
131
+ 18,self_attn.o_proj,0.00352678,0.01000,0.796
132
+ 18,mlp.up_proj,0.06900685,0.01000,0.379
133
+ 18,mlp.gate_proj,0.07904451,0.01000,0.397
134
+ 18,mlp.down_proj,0.02755920,0.01000,1.105
135
+ 19,self_attn.k_proj,0.16187871,0.01000,0.356
136
+ 19,self_attn.v_proj,0.20003729,0.01000,0.351
137
+ 19,self_attn.q_proj,0.52686477,0.01000,0.369
138
+ 19,self_attn.o_proj,0.00656477,0.01000,0.893
139
+ 19,mlp.up_proj,0.08853976,0.01000,0.449
140
+ 19,mlp.gate_proj,0.08336402,0.01000,0.426
141
+ 19,mlp.down_proj,0.05588865,0.01000,1.080
142
+ 20,self_attn.k_proj,0.22524926,0.01000,-2.716
143
+ 20,self_attn.v_proj,0.26741582,0.01000,0.359
144
+ 20,self_attn.q_proj,0.65623856,0.01000,0.358
145
+ 20,self_attn.o_proj,0.00873903,0.01000,0.703
146
+ 20,mlp.up_proj,0.09712939,0.01000,0.365
147
+ 20,mlp.gate_proj,0.08698984,0.01000,0.385
148
+ 20,mlp.down_proj,0.06682739,0.01000,1.080
149
+ 21,self_attn.k_proj,0.39126575,0.01000,0.358
150
+ 21,self_attn.v_proj,0.50307965,0.01000,0.393
151
+ 21,self_attn.q_proj,1.09633744,0.01000,0.364
152
+ 21,self_attn.o_proj,0.01702069,0.01000,0.759
153
+ 21,mlp.up_proj,0.11749193,0.01000,0.390
154
+ 21,mlp.gate_proj,0.09473881,0.01000,0.367
155
+ 21,mlp.down_proj,0.09391166,0.01000,1.339
156
+ 22,self_attn.k_proj,0.42912284,0.01000,0.366
157
+ 22,self_attn.v_proj,0.62853205,0.01000,0.363
158
+ 22,self_attn.q_proj,1.13549972,0.01000,0.362
159
+ 22,self_attn.o_proj,0.01342478,0.01000,0.734
160
+ 22,mlp.up_proj,0.12709107,0.01000,0.371
161
+ 22,mlp.gate_proj,0.10018895,0.01000,0.380
162
+ 22,mlp.down_proj,0.10143830,0.01000,1.094
163
+ 23,self_attn.k_proj,0.59195518,0.01000,0.474
164
+ 23,self_attn.v_proj,0.68701136,0.01000,0.384
165
+ 23,self_attn.q_proj,1.32605648,0.01000,0.414
166
+ 23,self_attn.o_proj,0.01738492,0.01000,0.719
167
+ 23,mlp.up_proj,0.14314744,0.01000,0.361
168
+ 23,mlp.gate_proj,0.11007850,0.01000,0.408
169
+ 23,mlp.down_proj,0.10754839,0.01000,1.478
170
+ 24,self_attn.k_proj,1.00415301,0.01000,0.361
171
+ 24,self_attn.v_proj,1.12105525,0.01000,0.355
172
+ 24,self_attn.q_proj,2.56474996,0.01000,0.358
173
+ 24,self_attn.o_proj,0.02551685,0.01000,0.712
174
+ 24,mlp.up_proj,0.13545924,0.01000,0.408
175
+ 24,mlp.gate_proj,0.10024798,0.01000,0.363
176
+ 24,mlp.down_proj,0.10790002,0.01000,1.191
177
+ 25,self_attn.k_proj,1.19017565,0.01000,0.356
178
+ 25,self_attn.v_proj,1.88630354,0.01000,0.358
179
+ 25,self_attn.q_proj,3.16219616,0.01000,0.353
180
+ 25,self_attn.o_proj,0.03715168,0.01000,0.753
181
+ 25,mlp.up_proj,0.13330801,0.01000,0.360
182
+ 25,mlp.gate_proj,0.09387642,0.01000,0.368
183
+ 25,mlp.down_proj,0.13108285,0.01000,1.079
184
+ 26,self_attn.k_proj,1.18263948,0.01000,0.436
185
+ 26,self_attn.v_proj,1.67280781,0.01000,0.470
186
+ 26,self_attn.q_proj,3.34765911,0.01000,0.454
187
+ 26,self_attn.o_proj,0.09499875,0.01000,0.728
188
+ 26,mlp.up_proj,0.14457943,0.01000,0.355
189
+ 26,mlp.gate_proj,0.10359854,0.01000,0.367
190
+ 26,mlp.down_proj,0.20188543,0.01000,1.095
191
+ 27,self_attn.k_proj,0.88096058,0.01000,0.350
192
+ 27,self_attn.v_proj,1.04464459,0.01000,0.357
193
+ 27,self_attn.q_proj,1.89896679,0.01000,0.349
194
+ 27,self_attn.o_proj,0.05569953,0.01000,0.722
195
+ 27,mlp.up_proj,0.25829488,0.01000,0.365
196
+ 27,mlp.gate_proj,0.24046963,0.01000,0.367
197
+ 27,mlp.down_proj,0.23538056,0.01000,1.094
quantize_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 8,
3
+ "group_size": 128,
4
+ "desc_act": true,
5
+ "sym": true,
6
+ "lm_head": false,
7
+ "quant_method": "gptq",
8
+ "checkpoint_format": "gptq",
9
+ "pack_dtype": "int32",
10
+ "meta": {
11
+ "quantizer": [
12
+ "gptqmodel:2.2.0"
13
+ ],
14
+ "uri": "https://github.com/modelcloud/gptqmodel",
15
+ "damp_percent": 0.01,
16
+ "damp_auto_increment": 0.0025,
17
+ "static_groups": false,
18
+ "true_sequential": true,
19
+ "mse": 0.0
20
+ }
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<unk>"
25
+ }
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 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<unk>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2TokenizerFast",
239
+ "unk_token": null,
240
+ "_commit_hash": null
241
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff