JunHowie commited on
Commit
9c92e03
·
verified ·
1 Parent(s): 876be8b

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": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
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 sha256:389183cc1d4900cc187474e8428d3f9799d7095c7d1ae6bde68e7abcf6676608
3
+ size 2067058568
quant_log.csv ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.00021213,0.01000,1.035
3
+ 0,self_attn.v_proj,0.00018730,0.01000,0.881
4
+ 0,self_attn.q_proj,0.00043831,0.01000,0.853
5
+ 0,self_attn.o_proj,0.00058800,0.01000,0.735
6
+ 0,mlp.up_proj,0.00271002,0.01000,0.783
7
+ 0,mlp.gate_proj,0.00414380,0.01000,0.788
8
+ 0,mlp.down_proj,0.00101138,0.01000,2.453
9
+ 1,self_attn.k_proj,0.00014310,0.01000,0.755
10
+ 1,self_attn.v_proj,0.00014349,0.01000,0.759
11
+ 1,self_attn.q_proj,0.00029935,0.01000,0.840
12
+ 1,self_attn.o_proj,0.00017923,0.01000,0.856
13
+ 1,mlp.up_proj,0.02669135,0.01000,0.789
14
+ 1,mlp.gate_proj,0.06627879,0.01000,0.774
15
+ 1,mlp.down_proj,0.00148649,0.01000,0.413
16
+ 2,self_attn.k_proj,0.00028350,0.01000,0.949
17
+ 2,self_attn.v_proj,0.00028310,0.01000,1.003
18
+ 2,self_attn.q_proj,0.00062501,0.01000,1.154
19
+ 2,self_attn.o_proj,0.00031052,0.01000,0.932
20
+ 2,mlp.up_proj,0.02402654,0.01000,1.073
21
+ 2,mlp.gate_proj,0.05953344,0.01000,1.074
22
+ 2,mlp.down_proj,4.57651949,0.01000,3.092
23
+ 3,self_attn.k_proj,0.00224831,0.01000,1.054
24
+ 3,self_attn.v_proj,0.00228381,0.01000,0.952
25
+ 3,self_attn.q_proj,0.00443252,0.01000,1.070
26
+ 3,self_attn.o_proj,0.00053862,0.01000,0.925
27
+ 3,mlp.up_proj,0.03297839,0.01000,0.811
28
+ 3,mlp.gate_proj,0.07683422,0.01000,0.784
29
+ 3,mlp.down_proj,0.00399093,0.01000,2.406
30
+ 4,self_attn.k_proj,0.00204805,0.01000,0.955
31
+ 4,self_attn.v_proj,0.00223531,0.01000,0.850
32
+ 4,self_attn.q_proj,0.00425037,0.01000,0.808
33
+ 4,self_attn.o_proj,0.00113138,0.01000,-1.498
34
+ 4,mlp.up_proj,0.03638201,0.01000,0.813
35
+ 4,mlp.gate_proj,0.07686634,0.01000,0.811
36
+ 4,mlp.down_proj,0.00542831,0.01000,2.623
37
+ 5,self_attn.k_proj,0.00291197,0.01000,0.753
38
+ 5,self_attn.v_proj,0.00323620,0.01000,0.751
39
+ 5,self_attn.q_proj,0.00650772,0.01000,0.793
40
+ 5,self_attn.o_proj,0.00159497,0.01000,0.814
41
+ 5,mlp.up_proj,0.02745156,0.01000,1.097
42
+ 5,mlp.gate_proj,0.04014464,0.01000,1.274
43
+ 5,mlp.down_proj,0.00701444,0.01000,3.667
44
+ 6,self_attn.k_proj,0.00282208,0.01000,1.024
45
+ 6,self_attn.v_proj,0.00264384,0.01000,1.299
46
+ 6,self_attn.q_proj,0.00581112,0.01000,1.321
47
+ 6,self_attn.o_proj,0.00170272,0.01000,0.995
48
+ 6,mlp.up_proj,0.03806943,0.01000,1.123
49
+ 6,mlp.gate_proj,0.05433278,0.01000,1.157
50
+ 6,mlp.down_proj,0.01055793,0.01000,3.480
51
+ 7,self_attn.k_proj,0.00579185,0.01000,1.144
52
+ 7,self_attn.v_proj,0.00649086,0.01000,1.215
53
+ 7,self_attn.q_proj,0.01329568,0.01000,1.317
54
+ 7,self_attn.o_proj,0.00251324,0.01000,1.081
55
+ 7,mlp.up_proj,0.05078189,0.01000,1.070
56
+ 7,mlp.gate_proj,0.07666416,0.01000,1.111
57
+ 7,mlp.down_proj,0.01217680,0.01000,3.491
58
+ 8,self_attn.k_proj,0.00822579,0.01000,-1.198
59
+ 8,self_attn.v_proj,0.00778028,0.01000,1.051
60
+ 8,self_attn.q_proj,0.01691954,0.01000,1.259
61
+ 8,self_attn.o_proj,0.00198344,0.01000,1.236
62
+ 8,mlp.up_proj,0.05237917,0.01000,1.217
63
+ 8,mlp.gate_proj,0.07096568,0.01000,1.496
64
+ 8,mlp.down_proj,0.01507390,0.01000,3.506
65
+ 9,self_attn.k_proj,0.01486574,0.01000,1.089
66
+ 9,self_attn.v_proj,0.01466936,0.01000,1.134
67
+ 9,self_attn.q_proj,0.03340287,0.01000,1.463
68
+ 9,self_attn.o_proj,0.00612606,0.01000,0.969
69
+ 9,mlp.up_proj,0.05645886,0.01000,1.021
70
+ 9,mlp.gate_proj,0.07014520,0.01000,1.012
71
+ 9,mlp.down_proj,0.02353373,0.01000,3.295
72
+ 10,self_attn.k_proj,0.01207330,0.01000,0.952
73
+ 10,self_attn.v_proj,0.01267793,0.01000,0.941
74
+ 10,self_attn.q_proj,0.02684752,0.01000,1.084
75
+ 10,self_attn.o_proj,0.00635564,0.01000,-1.964
76
+ 10,mlp.up_proj,0.05980083,0.01000,1.030
77
+ 10,mlp.gate_proj,0.07126677,0.01000,1.037
78
+ 10,mlp.down_proj,0.03233313,0.01000,3.238
79
+ 11,self_attn.k_proj,0.02337834,0.01000,0.939
80
+ 11,self_attn.v_proj,0.02054827,0.01000,0.976
81
+ 11,self_attn.q_proj,0.05309612,0.01000,1.126
82
+ 11,self_attn.o_proj,0.01651588,0.01000,0.995
83
+ 11,mlp.up_proj,0.06393285,0.01000,1.041
84
+ 11,mlp.gate_proj,0.06634086,0.01000,1.084
85
+ 11,mlp.down_proj,0.04003984,0.01000,3.541
86
+ 12,self_attn.k_proj,0.02390475,0.01000,1.025
87
+ 12,self_attn.v_proj,0.02381455,0.01000,1.001
88
+ 12,self_attn.q_proj,0.05352846,0.01000,1.239
89
+ 12,self_attn.o_proj,0.00940318,0.01000,0.999
90
+ 12,mlp.up_proj,0.06354553,0.01000,1.243
91
+ 12,mlp.gate_proj,0.06274655,0.01000,1.282
92
+ 12,mlp.down_proj,0.03782850,0.01000,3.660
93
+ 13,self_attn.k_proj,0.02883048,0.01000,1.263
94
+ 13,self_attn.v_proj,0.03046086,0.01000,1.332
95
+ 13,self_attn.q_proj,0.07497985,0.01000,1.355
96
+ 13,self_attn.o_proj,0.01249085,0.01000,1.076
97
+ 13,mlp.up_proj,0.06711861,0.01000,1.060
98
+ 13,mlp.gate_proj,0.06596832,0.01000,1.251
99
+ 13,mlp.down_proj,0.04400112,0.01000,3.370
100
+ 14,self_attn.k_proj,0.04748870,0.01000,1.103
101
+ 14,self_attn.v_proj,0.04818982,0.01000,1.470
102
+ 14,self_attn.q_proj,0.11405970,0.01000,1.620
103
+ 14,self_attn.o_proj,0.01503194,0.01000,1.176
104
+ 14,mlp.up_proj,0.07211645,0.01000,1.103
105
+ 14,mlp.gate_proj,0.06923115,0.01000,1.214
106
+ 14,mlp.down_proj,0.05922792,0.01000,4.051
107
+ 15,self_attn.k_proj,0.08816600,0.01000,1.003
108
+ 15,self_attn.v_proj,0.10396016,0.01000,1.061
109
+ 15,self_attn.q_proj,0.25768161,0.01000,1.312
110
+ 15,self_attn.o_proj,0.02884788,0.01000,1.034
111
+ 15,mlp.up_proj,0.08229292,0.01000,1.056
112
+ 15,mlp.gate_proj,0.07718438,0.01000,1.188
113
+ 15,mlp.down_proj,0.08335496,0.01000,3.383
114
+ 16,self_attn.k_proj,0.13276498,0.01000,1.286
115
+ 16,self_attn.v_proj,0.11645139,0.01000,1.375
116
+ 16,self_attn.q_proj,0.32413393,0.01000,1.442
117
+ 16,self_attn.o_proj,0.03403146,0.01000,1.186
118
+ 16,mlp.up_proj,0.10164497,0.01000,1.307
119
+ 16,mlp.gate_proj,0.08934272,0.01000,-0.819
120
+ 16,mlp.down_proj,0.20673957,0.01000,5.254
121
+ 17,self_attn.k_proj,0.32843712,0.01000,1.008
122
+ 17,self_attn.v_proj,0.36150685,0.01000,1.159
123
+ 17,self_attn.q_proj,0.87287247,0.01000,1.315
124
+ 17,self_attn.o_proj,0.09322287,0.01000,1.121
125
+ 17,mlp.up_proj,0.14729175,0.01000,1.567
126
+ 17,mlp.gate_proj,0.12632927,0.01000,1.521
127
+ 17,mlp.down_proj,0.28624713,0.01000,3.447
128
+ 18,self_attn.k_proj,0.36269355,0.01000,1.153
129
+ 18,self_attn.v_proj,0.35573715,0.01000,1.131
130
+ 18,self_attn.q_proj,0.96067095,0.01000,1.429
131
+ 18,self_attn.o_proj,0.07416759,0.01000,0.958
132
+ 18,mlp.up_proj,0.19080156,0.01000,1.128
133
+ 18,mlp.gate_proj,0.16498668,0.01000,1.139
134
+ 18,mlp.down_proj,0.46512970,0.01000,4.067
135
+ 19,self_attn.k_proj,0.63042080,0.01000,1.001
136
+ 19,self_attn.v_proj,0.66970766,0.01000,1.076
137
+ 19,self_attn.q_proj,1.71944344,0.01000,1.207
138
+ 19,self_attn.o_proj,0.14147554,0.01000,1.061
139
+ 19,mlp.up_proj,0.26083666,0.01000,1.084
140
+ 19,mlp.gate_proj,0.21945253,0.01000,1.142
141
+ 19,mlp.down_proj,1.08294749,0.01000,5.246
142
+ 20,self_attn.k_proj,1.05661917,0.01000,1.372
143
+ 20,self_attn.v_proj,1.12255192,0.01000,1.604
144
+ 20,self_attn.q_proj,2.70668817,0.01000,1.736
145
+ 20,self_attn.o_proj,0.21295784,0.01000,1.384
146
+ 20,mlp.up_proj,0.33657771,0.01000,1.446
147
+ 20,mlp.gate_proj,0.29224217,0.01000,1.786
148
+ 20,mlp.down_proj,1.65073872,0.01000,3.429
149
+ 21,self_attn.k_proj,1.72003376,0.01000,0.919
150
+ 21,self_attn.v_proj,1.95115852,0.01000,0.935
151
+ 21,self_attn.q_proj,4.07931805,0.01000,1.037
152
+ 21,self_attn.o_proj,0.34855676,0.01000,1.071
153
+ 21,mlp.up_proj,0.42343667,0.01000,1.001
154
+ 21,mlp.gate_proj,0.36413121,0.01000,1.068
155
+ 21,mlp.down_proj,2.29638433,0.01000,3.512
156
+ 22,self_attn.k_proj,2.07225657,0.01000,1.009
157
+ 22,self_attn.v_proj,2.67138195,0.01000,0.974
158
+ 22,self_attn.q_proj,4.89232826,0.01000,1.133
159
+ 22,self_attn.o_proj,0.32573640,0.01000,0.979
160
+ 22,mlp.up_proj,0.48066208,0.01000,0.988
161
+ 22,mlp.gate_proj,0.42026463,0.01000,-1.227
162
+ 22,mlp.down_proj,2.75672221,0.01000,3.346
163
+ 23,self_attn.k_proj,2.89560223,0.01000,-0.880
164
+ 23,self_attn.v_proj,3.34686661,0.01000,1.224
165
+ 23,self_attn.q_proj,5.94703102,0.01000,1.648
166
+ 23,self_attn.o_proj,0.36002848,0.01000,1.238
167
+ 23,mlp.up_proj,0.57230163,0.01000,1.349
168
+ 23,mlp.gate_proj,0.50760889,0.01000,1.346
169
+ 23,mlp.down_proj,3.04040956,0.01000,3.433
170
+ 24,self_attn.k_proj,4.98425198,0.01000,1.329
171
+ 24,self_attn.v_proj,5.90884781,0.01000,1.486
172
+ 24,self_attn.q_proj,11.70157814,0.01000,1.424
173
+ 24,self_attn.o_proj,0.54404330,0.01000,1.189
174
+ 24,mlp.up_proj,0.56059366,0.01000,1.400
175
+ 24,mlp.gate_proj,0.48390830,0.01000,1.230
176
+ 24,mlp.down_proj,3.49181962,0.01000,3.296
177
+ 25,self_attn.k_proj,5.89854097,0.01000,1.143
178
+ 25,self_attn.v_proj,9.15399933,0.01000,1.175
179
+ 25,self_attn.q_proj,13.68663883,0.01000,1.384
180
+ 25,self_attn.o_proj,0.68277156,0.01000,1.290
181
+ 25,mlp.up_proj,0.54084748,0.01000,1.356
182
+ 25,mlp.gate_proj,0.45770794,0.01000,-0.815
183
+ 25,mlp.down_proj,4.11712790,0.01000,2.954
184
+ 26,self_attn.k_proj,5.72237206,0.01000,-1.172
185
+ 26,self_attn.v_proj,8.08352089,0.01000,0.965
186
+ 26,self_attn.q_proj,14.01196480,0.01000,1.138
187
+ 26,self_attn.o_proj,1.53745091,0.01000,0.754
188
+ 26,mlp.up_proj,0.53795302,0.01000,0.806
189
+ 26,mlp.gate_proj,0.46326143,0.01000,0.799
190
+ 26,mlp.down_proj,5.13344669,0.01000,0.696
191
+ 27,self_attn.k_proj,2.93648863,0.01000,0.916
192
+ 27,self_attn.v_proj,3.24627113,0.01000,0.912
193
+ 27,self_attn.q_proj,6.04585409,0.01000,0.859
194
+ 27,self_attn.o_proj,0.87356722,0.01000,0.880
195
+ 27,mlp.up_proj,0.71681577,0.01000,0.853
196
+ 27,mlp.gate_proj,0.72430158,0.01000,0.804
197
+ 27,mlp.down_proj,6.90643501,0.01000,2.481
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