AlphaGaO commited on
Commit
fe96820
·
verified ·
1 Parent(s): f63afc5

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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4,
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 sha256:2f211f49266ae594ec5ad1712490912147924b5f3b2cf6348b8289b1bf3975eb
3
+ size 541343840
quant_log.csv ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.11147800,0.01000,0.458
3
+ 0,self_attn.v_proj,0.08630855,0.01000,0.219
4
+ 0,self_attn.q_proj,0.25900897,0.01000,0.222
5
+ 0,self_attn.o_proj,0.07599418,0.01000,0.450
6
+ 0,mlp.up_proj,1.53504455,0.01000,0.232
7
+ 0,mlp.gate_proj,3.04540825,0.01000,0.218
8
+ 0,mlp.down_proj,0.08534984,0.01000,0.677
9
+ 1,self_attn.k_proj,0.05401947,0.01000,0.235
10
+ 1,self_attn.v_proj,0.05086039,0.01000,0.220
11
+ 1,self_attn.q_proj,0.12237675,0.01000,0.220
12
+ 1,self_attn.o_proj,0.01379651,0.01000,0.451
13
+ 1,mlp.up_proj,5.61016464,0.01000,0.231
14
+ 1,mlp.gate_proj,19.20188904,0.01000,0.219
15
+ 1,mlp.down_proj,0.10827485,0.01000,0.678
16
+ 2,self_attn.k_proj,0.10099948,0.01000,0.233
17
+ 2,self_attn.v_proj,0.09610087,0.01000,0.219
18
+ 2,self_attn.q_proj,0.23747258,0.01000,0.219
19
+ 2,self_attn.o_proj,0.02400546,0.01000,0.450
20
+ 2,mlp.up_proj,4.73568106,0.01000,0.232
21
+ 2,mlp.gate_proj,13.18591118,0.01000,0.220
22
+ 2,mlp.down_proj,4.35225487,0.01000,0.682
23
+ 3,self_attn.k_proj,0.84643447,0.01000,0.236
24
+ 3,self_attn.v_proj,0.85565448,0.01000,0.221
25
+ 3,self_attn.q_proj,1.74525285,0.01000,0.222
26
+ 3,self_attn.o_proj,0.05005993,0.01000,0.452
27
+ 3,mlp.up_proj,6.21245098,0.01000,0.232
28
+ 3,mlp.gate_proj,16.04592896,0.01000,0.222
29
+ 3,mlp.down_proj,0.34597254,0.01000,0.682
30
+ 4,self_attn.k_proj,0.78725469,0.01000,0.234
31
+ 4,self_attn.v_proj,0.80693889,0.01000,0.220
32
+ 4,self_attn.q_proj,1.57810068,0.01000,0.222
33
+ 4,self_attn.o_proj,0.10350977,0.01000,0.453
34
+ 4,mlp.up_proj,6.71505690,0.01000,0.234
35
+ 4,mlp.gate_proj,15.28214741,0.01000,0.222
36
+ 4,mlp.down_proj,0.41565913,0.01000,0.681
37
+ 5,self_attn.k_proj,1.20404196,0.01000,0.234
38
+ 5,self_attn.v_proj,1.30846250,0.01000,0.221
39
+ 5,self_attn.q_proj,2.90022326,0.01000,0.221
40
+ 5,self_attn.o_proj,0.11212036,0.01000,0.453
41
+ 5,mlp.up_proj,6.31282043,0.01000,0.232
42
+ 5,mlp.gate_proj,10.49855423,0.01000,0.219
43
+ 5,mlp.down_proj,0.48409772,0.01000,0.681
44
+ 6,self_attn.k_proj,0.93520665,0.01000,0.234
45
+ 6,self_attn.v_proj,0.87466520,0.01000,0.221
46
+ 6,self_attn.q_proj,2.08447576,0.01000,0.233
47
+ 6,self_attn.o_proj,0.11541309,0.01000,0.453
48
+ 6,mlp.up_proj,8.37039280,0.01000,0.232
49
+ 6,mlp.gate_proj,13.32755280,0.01000,0.221
50
+ 6,mlp.down_proj,0.70866877,0.01000,0.682
51
+ 7,self_attn.k_proj,1.72509587,0.01000,0.232
52
+ 7,self_attn.v_proj,1.93890357,0.01000,0.217
53
+ 7,self_attn.q_proj,4.17893887,0.01000,0.215
54
+ 7,self_attn.o_proj,0.14572459,0.01000,0.443
55
+ 7,mlp.up_proj,9.48272038,0.01000,0.227
56
+ 7,mlp.gate_proj,15.29617691,0.01000,0.215
57
+ 7,mlp.down_proj,0.81154561,0.01000,0.710
58
+ 8,self_attn.k_proj,2.27103615,0.01000,0.238
59
+ 8,self_attn.v_proj,2.20937443,0.01000,0.224
60
+ 8,self_attn.q_proj,5.15229893,0.01000,0.241
61
+ 8,self_attn.o_proj,0.17240790,0.01000,0.446
62
+ 8,mlp.up_proj,10.42674160,0.01000,0.243
63
+ 8,mlp.gate_proj,16.20728493,0.01000,0.231
64
+ 8,mlp.down_proj,1.09275961,0.01000,0.822
65
+ 9,self_attn.k_proj,4.16666269,0.01000,1.138
66
+ 9,self_attn.v_proj,4.43104601,0.01000,0.376
67
+ 9,self_attn.q_proj,10.31816101,0.01000,0.415
68
+ 9,self_attn.o_proj,0.31887323,0.01000,0.840
69
+ 9,mlp.up_proj,12.31618500,0.01000,1.191
70
+ 9,mlp.gate_proj,19.54656982,0.01000,1.154
71
+ 9,mlp.down_proj,1.64975393,0.01000,2.770
72
+ 10,self_attn.k_proj,3.93787289,0.01000,0.553
73
+ 10,self_attn.v_proj,4.10471725,0.01000,1.859
74
+ 10,self_attn.q_proj,9.49951458,0.01000,1.888
75
+ 10,self_attn.o_proj,0.27260423,0.01000,0.464
76
+ 10,mlp.up_proj,12.69118309,0.01000,0.238
77
+ 10,mlp.gate_proj,20.18230057,0.01000,0.225
78
+ 10,mlp.down_proj,2.11628580,0.01000,0.696
79
+ 11,self_attn.k_proj,7.30851555,0.01000,0.237
80
+ 11,self_attn.v_proj,6.77896643,0.01000,0.224
81
+ 11,self_attn.q_proj,19.34665871,0.01000,0.225
82
+ 11,self_attn.o_proj,0.66791785,0.01000,0.476
83
+ 11,mlp.up_proj,13.51113892,0.01000,0.236
84
+ 11,mlp.gate_proj,17.58659363,0.01000,0.224
85
+ 11,mlp.down_proj,2.87829471,0.01000,0.691
86
+ 12,self_attn.k_proj,7.20854664,0.01000,0.238
87
+ 12,self_attn.v_proj,7.45390940,0.01000,0.224
88
+ 12,self_attn.q_proj,19.43825531,0.01000,0.225
89
+ 12,self_attn.o_proj,0.30023530,0.01000,0.460
90
+ 12,mlp.up_proj,12.92345810,0.01000,0.238
91
+ 12,mlp.gate_proj,15.76972866,0.01000,0.225
92
+ 12,mlp.down_proj,2.75112391,0.01000,0.742
93
+ 13,self_attn.k_proj,6.89573908,0.01000,0.238
94
+ 13,self_attn.v_proj,8.19425392,0.01000,0.224
95
+ 13,self_attn.q_proj,20.47906685,0.01000,0.224
96
+ 13,self_attn.o_proj,0.44192302,0.01000,0.460
97
+ 13,mlp.up_proj,13.60263252,0.01000,0.237
98
+ 13,mlp.gate_proj,16.85786819,0.01000,0.224
99
+ 13,mlp.down_proj,2.74464965,0.01000,0.694
100
+ 14,self_attn.k_proj,9.22984314,0.01000,0.238
101
+ 14,self_attn.v_proj,10.04637337,0.01000,0.222
102
+ 14,self_attn.q_proj,25.66234970,0.01000,0.224
103
+ 14,self_attn.o_proj,0.47217572,0.01000,0.462
104
+ 14,mlp.up_proj,15.06594086,0.01000,0.235
105
+ 14,mlp.gate_proj,18.42022133,0.01000,0.223
106
+ 14,mlp.down_proj,3.77921104,0.01000,0.691
107
+ 15,self_attn.k_proj,16.64938736,0.01000,0.238
108
+ 15,self_attn.v_proj,20.63287735,0.01000,0.223
109
+ 15,self_attn.q_proj,52.25179291,0.01000,0.224
110
+ 15,self_attn.o_proj,0.78019929,0.01000,0.516
111
+ 15,mlp.up_proj,16.64070892,0.01000,1.398
112
+ 15,mlp.gate_proj,19.79901123,0.01000,1.352
113
+ 15,mlp.down_proj,3.98885012,0.01000,1.246
114
+ 16,self_attn.k_proj,23.15541840,0.01000,0.869
115
+ 16,self_attn.v_proj,21.59778023,0.01000,0.406
116
+ 16,self_attn.q_proj,65.96479797,0.01000,0.817
117
+ 16,self_attn.o_proj,1.10674870,0.01000,1.846
118
+ 16,mlp.up_proj,18.38120270,0.01000,0.439
119
+ 16,mlp.gate_proj,20.62617493,0.01000,0.633
120
+ 16,mlp.down_proj,7.29946709,0.01000,4.478
121
+ 17,self_attn.k_proj,50.91555786,0.01000,0.994
122
+ 17,self_attn.v_proj,62.10039520,0.01000,1.044
123
+ 17,self_attn.q_proj,153.88165283,0.01000,1.083
124
+ 17,self_attn.o_proj,2.35713625,0.01000,0.461
125
+ 17,mlp.up_proj,28.26027870,0.01000,0.235
126
+ 17,mlp.gate_proj,32.26748657,0.01000,0.223
127
+ 17,mlp.down_proj,8.62757301,0.01000,0.693
128
+ 18,self_attn.k_proj,47.62117004,0.01000,0.237
129
+ 18,self_attn.v_proj,49.91074753,0.01000,0.224
130
+ 18,self_attn.q_proj,148.18688965,0.01000,0.224
131
+ 18,self_attn.o_proj,2.07341361,0.01000,0.459
132
+ 18,mlp.up_proj,34.44437408,0.01000,0.237
133
+ 18,mlp.gate_proj,39.49178314,0.01000,0.224
134
+ 18,mlp.down_proj,13.71113110,0.01000,0.692
135
+ 19,self_attn.k_proj,80.47894287,0.01000,0.239
136
+ 19,self_attn.v_proj,90.67363739,0.01000,0.224
137
+ 19,self_attn.q_proj,264.28625488,0.01000,0.232
138
+ 19,self_attn.o_proj,4.05158710,0.01000,0.460
139
+ 19,mlp.up_proj,43.40443420,0.01000,0.235
140
+ 19,mlp.gate_proj,41.79368210,0.01000,0.224
141
+ 19,mlp.down_proj,24.53729630,0.01000,0.693
142
+ 20,self_attn.k_proj,111.07940674,0.01000,0.237
143
+ 20,self_attn.v_proj,125.48833466,0.01000,0.223
144
+ 20,self_attn.q_proj,326.05548096,0.01000,0.224
145
+ 20,self_attn.o_proj,5.44219112,0.01000,0.461
146
+ 20,mlp.up_proj,48.42160797,0.01000,0.236
147
+ 20,mlp.gate_proj,43.89644623,0.01000,0.223
148
+ 20,mlp.down_proj,28.64599991,0.01000,0.692
149
+ 21,self_attn.k_proj,182.44018555,0.01000,0.238
150
+ 21,self_attn.v_proj,234.88687134,0.01000,0.224
151
+ 21,self_attn.q_proj,529.24645996,0.01000,0.234
152
+ 21,self_attn.o_proj,9.00667953,0.01000,0.462
153
+ 21,mlp.up_proj,57.38450623,0.01000,0.237
154
+ 21,mlp.gate_proj,47.00152588,0.01000,0.224
155
+ 21,mlp.down_proj,37.96351242,0.01000,0.700
156
+ 22,self_attn.k_proj,201.98219299,0.01000,0.240
157
+ 22,self_attn.v_proj,281.84835815,0.01000,0.238
158
+ 22,self_attn.q_proj,535.36541748,0.01000,0.227
159
+ 22,self_attn.o_proj,6.89678383,0.01000,0.476
160
+ 22,mlp.up_proj,60.97026062,0.01000,0.238
161
+ 22,mlp.gate_proj,48.76005554,0.01000,0.225
162
+ 22,mlp.down_proj,38.75309753,0.01000,0.698
163
+ 23,self_attn.k_proj,269.43804932,0.01000,0.239
164
+ 23,self_attn.v_proj,304.47036743,0.01000,0.225
165
+ 23,self_attn.q_proj,607.39343262,0.01000,0.226
166
+ 23,self_attn.o_proj,13.71835327,0.01000,0.464
167
+ 23,mlp.up_proj,68.53395844,0.01000,0.272
168
+ 23,mlp.gate_proj,53.10926056,0.01000,0.257
169
+ 23,mlp.down_proj,39.62349701,0.01000,0.691
170
+ 24,self_attn.k_proj,446.88357544,0.01000,0.235
171
+ 24,self_attn.v_proj,481.67712402,0.01000,0.221
172
+ 24,self_attn.q_proj,1182.38500977,0.01000,0.223
173
+ 24,self_attn.o_proj,11.81310463,0.01000,0.464
174
+ 24,mlp.up_proj,64.03303528,0.01000,0.235
175
+ 24,mlp.gate_proj,47.69067764,0.01000,0.222
176
+ 24,mlp.down_proj,43.55418777,0.01000,0.694
177
+ 25,self_attn.k_proj,518.00433350,0.01000,0.238
178
+ 25,self_attn.v_proj,774.28698730,0.01000,0.223
179
+ 25,self_attn.q_proj,1437.99023438,0.01000,0.224
180
+ 25,self_attn.o_proj,16.01141739,0.01000,0.464
181
+ 25,mlp.up_proj,60.59749222,0.01000,0.235
182
+ 25,mlp.gate_proj,42.82708359,0.01000,0.221
183
+ 25,mlp.down_proj,52.50085831,0.01000,0.694
184
+ 26,self_attn.k_proj,481.84396362,0.01000,0.239
185
+ 26,self_attn.v_proj,666.03979492,0.01000,0.224
186
+ 26,self_attn.q_proj,1392.31616211,0.01000,0.225
187
+ 26,self_attn.o_proj,32.51730347,0.01000,0.461
188
+ 26,mlp.up_proj,63.72230148,0.01000,0.237
189
+ 26,mlp.gate_proj,45.98903656,0.01000,0.224
190
+ 26,mlp.down_proj,73.96157837,0.01000,0.696
191
+ 27,self_attn.k_proj,372.15234375,0.01000,0.240
192
+ 27,self_attn.v_proj,453.49694824,0.01000,0.224
193
+ 27,self_attn.q_proj,820.22900391,0.01000,0.225
194
+ 27,self_attn.o_proj,21.22069931,0.01000,0.464
195
+ 27,mlp.up_proj,103.78501892,0.01000,0.236
196
+ 27,mlp.gate_proj,95.20819092,0.01000,0.225
197
+ 27,mlp.down_proj,89.54586029,0.01000,0.693
quantize_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
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