itdainb commited on
Commit
d30c884
·
verified ·
1 Parent(s): 48082f5

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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 4096,
14
+ "max_window_layers": 48,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 2,
19
+ "quantization_config": {
20
+ "bits": 4,
21
+ "checkpoint_format": "gptq",
22
+ "desc_act": true,
23
+ "group_size": 128,
24
+ "lm_head": false,
25
+ "meta": {
26
+ "damp_auto_increment": 0.0025,
27
+ "damp_percent": 0.01,
28
+ "mse": 0.0,
29
+ "quantizer": [
30
+ "gptqmodel:1.9.0"
31
+ ],
32
+ "static_groups": false,
33
+ "true_sequential": true,
34
+ "uri": "https://github.com/modelcloud/gptqmodel"
35
+ },
36
+ "pack_dtype": "int32",
37
+ "quant_method": "gptq",
38
+ "sym": true
39
+ },
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": null,
42
+ "rope_theta": 1000000.0,
43
+ "sliding_window": 32768,
44
+ "tie_word_embeddings": false,
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.50.3",
47
+ "use_cache": true,
48
+ "use_mrope": false,
49
+ "use_sliding_window": false,
50
+ "vocab_size": 151936
51
+ }
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 sha256:022e4f09f6b5cfd7681deafa5cddd694486921185fa6a3f00dd38b4a7060ce33
3
+ size 918766280
quant_log.csv ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,damp,time
2
+ 0,self_attn.k_proj,0.03502,0.01000,0.600
3
+ 0,self_attn.v_proj,0.00149,0.01000,0.431
4
+ 0,self_attn.q_proj,0.10544,0.01000,0.358
5
+ 0,self_attn.o_proj,0.00012,0.01000,0.356
6
+ 0,mlp.up_proj,5.00789,0.01000,0.370
7
+ 0,mlp.gate_proj,6.02638,0.01000,0.368
8
+ 0,mlp.down_proj,0.01262,0.01000,1.998
9
+ 1,self_attn.k_proj,0.01558,0.01000,0.356
10
+ 1,self_attn.v_proj,0.00187,0.01000,0.354
11
+ 1,self_attn.q_proj,0.09073,0.01000,0.450
12
+ 1,self_attn.o_proj,0.00011,0.01000,0.356
13
+ 1,mlp.up_proj,3.36180,0.01000,0.375
14
+ 1,mlp.gate_proj,4.16244,0.01000,0.471
15
+ 1,mlp.down_proj,0.00165,0.01000,1.906
16
+ 2,self_attn.k_proj,0.60355,0.01000,0.353
17
+ 2,self_attn.v_proj,0.06793,0.01000,0.355
18
+ 2,self_attn.q_proj,1.13794,0.01000,0.444
19
+ 2,self_attn.o_proj,0.00234,0.01000,0.358
20
+ 2,mlp.up_proj,7.40313,0.01000,0.370
21
+ 2,mlp.gate_proj,11.70598,0.01000,0.473
22
+ 2,mlp.down_proj,0.01539,0.01000,1.897
23
+ 3,self_attn.k_proj,0.26456,0.01000,0.355
24
+ 3,self_attn.v_proj,0.04207,0.01000,0.351
25
+ 3,self_attn.q_proj,0.69332,0.01000,0.432
26
+ 3,self_attn.o_proj,0.00055,0.01000,0.357
27
+ 3,mlp.up_proj,6.28129,0.01000,0.373
28
+ 3,mlp.gate_proj,8.50286,0.01000,0.483
29
+ 3,mlp.down_proj,0.00720,0.01000,1.910
30
+ 4,self_attn.k_proj,1.69403,0.01000,0.362
31
+ 4,self_attn.v_proj,0.13846,0.01000,0.451
32
+ 4,self_attn.q_proj,3.39878,0.01000,0.428
33
+ 4,self_attn.o_proj,0.00950,0.01000,0.360
34
+ 4,mlp.up_proj,10.87261,0.01000,0.371
35
+ 4,mlp.gate_proj,18.55241,0.01000,0.504
36
+ 4,mlp.down_proj,0.14292,0.01000,1.348
37
+ 5,self_attn.k_proj,0.94710,0.01000,0.257
38
+ 5,self_attn.v_proj,0.16590,0.01000,0.271
39
+ 5,self_attn.q_proj,2.23485,0.01000,0.355
40
+ 5,self_attn.o_proj,0.00410,0.01000,0.255
41
+ 5,mlp.up_proj,10.98921,0.01000,0.270
42
+ 5,mlp.gate_proj,15.32189,0.01000,0.265
43
+ 5,mlp.down_proj,0.02995,0.01000,1.344
44
+ 6,self_attn.k_proj,2.68211,0.01000,0.257
45
+ 6,self_attn.v_proj,0.34881,0.01000,0.253
46
+ 6,self_attn.q_proj,5.39903,0.01000,0.344
47
+ 6,self_attn.o_proj,0.01885,0.01000,0.590
48
+ 6,mlp.up_proj,19.55389,0.01000,0.370
49
+ 6,mlp.gate_proj,34.42982,0.01000,0.472
50
+ 6,mlp.down_proj,0.10709,0.01000,1.898
51
+ 7,self_attn.k_proj,1.86686,0.01000,0.355
52
+ 7,self_attn.v_proj,0.40517,0.01000,0.350
53
+ 7,self_attn.q_proj,4.06289,0.01000,0.436
54
+ 7,self_attn.o_proj,0.00869,0.01000,0.356
55
+ 7,mlp.up_proj,15.71969,0.01000,0.372
56
+ 7,mlp.gate_proj,23.59863,0.01000,0.499
57
+ 7,mlp.down_proj,0.05564,0.01000,1.318
58
+ 8,self_attn.k_proj,1.88730,0.01000,0.251
59
+ 8,self_attn.v_proj,0.55043,0.01000,0.265
60
+ 8,self_attn.q_proj,4.32337,0.01000,0.341
61
+ 8,self_attn.o_proj,0.03835,0.01000,0.251
62
+ 8,mlp.up_proj,21.93264,0.01000,0.272
63
+ 8,mlp.gate_proj,34.87370,0.01000,0.376
64
+ 8,mlp.down_proj,0.12217,0.01000,1.326
65
+ 9,self_attn.k_proj,1.18920,0.01000,0.250
66
+ 9,self_attn.v_proj,0.32634,0.01000,0.306
67
+ 9,self_attn.q_proj,3.02042,0.01000,0.271
68
+ 9,self_attn.o_proj,0.00880,0.01000,0.254
69
+ 9,mlp.up_proj,16.77279,0.01000,0.272
70
+ 9,mlp.gate_proj,24.06133,0.01000,0.367
71
+ 9,mlp.down_proj,0.06775,0.01000,1.343
72
+ 10,self_attn.k_proj,2.82349,0.01000,0.252
73
+ 10,self_attn.v_proj,0.74898,0.01000,0.247
74
+ 10,self_attn.q_proj,6.31806,0.01000,0.339
75
+ 10,self_attn.o_proj,0.03610,0.01000,0.251
76
+ 10,mlp.up_proj,27.09812,0.01000,0.260
77
+ 10,mlp.gate_proj,59.46954,0.01000,0.377
78
+ 10,mlp.down_proj,0.15168,0.01000,1.332
79
+ 11,self_attn.k_proj,1.53766,0.01000,0.253
80
+ 11,self_attn.v_proj,0.40438,0.01000,0.260
81
+ 11,self_attn.q_proj,3.51694,0.01000,0.468
82
+ 11,self_attn.o_proj,0.00794,0.01000,0.409
83
+ 11,mlp.up_proj,17.42522,0.01000,0.267
84
+ 11,mlp.gate_proj,33.41463,0.01000,0.379
85
+ 11,mlp.down_proj,0.06716,0.01000,1.336
86
+ 12,self_attn.k_proj,2.71398,0.01000,0.255
87
+ 12,self_attn.v_proj,0.44769,0.01000,0.336
88
+ 12,self_attn.q_proj,4.99619,0.01000,0.322
89
+ 12,self_attn.o_proj,0.02493,0.01000,0.257
90
+ 12,mlp.up_proj,23.73990,0.01000,0.269
91
+ 12,mlp.gate_proj,35.98064,0.01000,0.367
92
+ 12,mlp.down_proj,0.13622,0.01000,1.381
93
+ 13,self_attn.k_proj,1.83977,0.01000,0.256
94
+ 13,self_attn.v_proj,0.32513,0.01000,0.254
95
+ 13,self_attn.q_proj,3.69291,0.01000,0.339
96
+ 13,self_attn.o_proj,0.00959,0.01000,0.254
97
+ 13,mlp.up_proj,17.12456,0.01000,0.269
98
+ 13,mlp.gate_proj,23.11242,0.01000,0.380
99
+ 13,mlp.down_proj,0.07700,0.01000,1.353
100
+ 14,self_attn.k_proj,4.11377,0.01000,0.272
101
+ 14,self_attn.v_proj,0.56398,0.01000,0.351
102
+ 14,self_attn.q_proj,7.77737,0.01000,0.292
103
+ 14,self_attn.o_proj,0.04280,0.01000,0.255
104
+ 14,mlp.up_proj,24.96210,0.01000,0.273
105
+ 14,mlp.gate_proj,34.15712,0.01000,0.364
106
+ 14,mlp.down_proj,0.13646,0.01000,1.338
107
+ 15,self_attn.k_proj,2.63422,0.01000,0.253
108
+ 15,self_attn.v_proj,0.39003,0.01000,0.340
109
+ 15,self_attn.q_proj,5.14377,0.01000,0.256
110
+ 15,self_attn.o_proj,0.01619,0.01000,0.254
111
+ 15,mlp.up_proj,16.05948,0.01000,0.273
112
+ 15,mlp.gate_proj,20.55264,0.01000,0.374
113
+ 15,mlp.down_proj,0.06390,0.01000,1.334
114
+ 16,self_attn.k_proj,2.12866,0.01000,0.264
115
+ 16,self_attn.v_proj,0.47042,0.01000,0.251
116
+ 16,self_attn.q_proj,6.88333,0.01000,0.299
117
+ 16,self_attn.o_proj,0.06486,0.01000,0.256
118
+ 16,mlp.up_proj,20.25186,0.01000,0.286
119
+ 16,mlp.gate_proj,27.96586,0.01000,0.489
120
+ 16,mlp.down_proj,0.08965,0.01000,1.931
121
+ 17,self_attn.k_proj,1.65464,0.01000,0.356
122
+ 17,self_attn.v_proj,0.42750,0.01000,0.353
123
+ 17,self_attn.q_proj,4.26713,0.01000,0.434
124
+ 17,self_attn.o_proj,0.00823,0.01000,0.358
125
+ 17,mlp.up_proj,14.15877,0.01000,0.380
126
+ 17,mlp.gate_proj,17.96412,0.01000,0.473
127
+ 17,mlp.down_proj,0.04496,0.01000,1.914
128
+ 18,self_attn.k_proj,6.82276,0.01000,0.356
129
+ 18,self_attn.v_proj,0.74098,0.01000,0.464
130
+ 18,self_attn.q_proj,16.49990,0.01000,0.361
131
+ 18,self_attn.o_proj,0.03458,0.01000,0.359
132
+ 18,mlp.up_proj,21.36189,0.01000,0.381
133
+ 18,mlp.gate_proj,26.75183,0.01000,0.500
134
+ 18,mlp.down_proj,0.09061,0.01000,1.923
135
+ 19,self_attn.k_proj,5.52928,0.01000,0.355
136
+ 19,self_attn.v_proj,0.85543,0.01000,0.356
137
+ 19,self_attn.q_proj,13.33852,0.01000,0.435
138
+ 19,self_attn.o_proj,0.01268,0.01000,0.357
139
+ 19,mlp.up_proj,14.30227,0.01000,0.372
140
+ 19,mlp.gate_proj,16.41010,0.01000,0.499
141
+ 19,mlp.down_proj,0.04469,0.01000,1.960
142
+ 20,self_attn.k_proj,2.39103,0.01000,0.356
143
+ 20,self_attn.v_proj,0.65044,0.01000,0.400
144
+ 20,self_attn.q_proj,5.50991,0.01000,0.445
145
+ 20,self_attn.o_proj,0.05966,0.01000,0.356
146
+ 20,mlp.up_proj,18.21964,0.01000,0.375
147
+ 20,mlp.gate_proj,25.80912,0.01000,0.476
148
+ 20,mlp.down_proj,0.07685,0.01000,1.894
149
+ 21,self_attn.k_proj,1.86779,0.01000,0.370
150
+ 21,self_attn.v_proj,0.48170,0.01000,0.463
151
+ 21,self_attn.q_proj,4.15237,0.01000,0.356
152
+ 21,self_attn.o_proj,0.01642,0.01000,0.357
153
+ 21,mlp.up_proj,14.35309,0.01000,0.373
154
+ 21,mlp.gate_proj,17.17359,0.01000,0.471
155
+ 21,mlp.down_proj,0.04145,0.01000,1.941
156
+ 22,self_attn.k_proj,7.57170,0.01000,0.357
157
+ 22,self_attn.v_proj,0.76554,0.01000,0.438
158
+ 22,self_attn.q_proj,16.30268,0.01000,0.360
159
+ 22,self_attn.o_proj,0.02961,0.01000,0.354
160
+ 22,mlp.up_proj,20.57209,0.01000,0.378
161
+ 22,mlp.gate_proj,23.87472,0.01000,0.469
162
+ 22,mlp.down_proj,0.08677,0.01000,1.888
163
+ 23,self_attn.k_proj,3.44012,0.01000,0.359
164
+ 23,self_attn.v_proj,0.73973,0.01000,0.462
165
+ 23,self_attn.q_proj,8.50972,0.01000,0.383
166
+ 23,self_attn.o_proj,0.01034,0.01000,0.354
167
+ 23,mlp.up_proj,14.92590,0.01000,0.380
168
+ 23,mlp.gate_proj,16.34019,0.01000,0.471
169
+ 23,mlp.down_proj,0.04388,0.01000,1.888
170
+ 24,self_attn.k_proj,2.68251,0.01000,0.356
171
+ 24,self_attn.v_proj,0.58842,0.01000,0.353
172
+ 24,self_attn.q_proj,6.38135,0.01000,0.427
173
+ 24,self_attn.o_proj,0.06894,0.01000,0.355
174
+ 24,mlp.up_proj,18.36766,0.01000,0.378
175
+ 24,mlp.gate_proj,22.58082,0.01000,0.493
176
+ 24,mlp.down_proj,0.07112,0.01000,1.890
177
+ 25,self_attn.k_proj,1.84232,0.01000,0.366
178
+ 25,self_attn.v_proj,0.38711,0.01000,0.459
179
+ 25,self_attn.q_proj,4.08449,0.01000,0.362
180
+ 25,self_attn.o_proj,0.00952,0.01000,0.357
181
+ 25,mlp.up_proj,13.12813,0.01000,0.375
182
+ 25,mlp.gate_proj,15.04545,0.01000,0.466
183
+ 25,mlp.down_proj,0.03564,0.01000,1.889
184
+ 26,self_attn.k_proj,4.76473,0.01000,0.356
185
+ 26,self_attn.v_proj,0.67035,0.01000,0.359
186
+ 26,self_attn.q_proj,10.89360,0.01000,0.428
187
+ 26,self_attn.o_proj,0.04611,0.01000,0.355
188
+ 26,mlp.up_proj,19.20356,0.01000,0.371
189
+ 26,mlp.gate_proj,23.04316,0.01000,0.484
190
+ 26,mlp.down_proj,0.08958,0.01000,1.966
191
+ 27,self_attn.k_proj,3.33627,0.01000,0.356
192
+ 27,self_attn.v_proj,0.54717,0.01000,0.425
193
+ 27,self_attn.q_proj,7.89752,0.01000,0.435
194
+ 27,self_attn.o_proj,0.01556,0.01000,0.353
195
+ 27,mlp.up_proj,13.69726,0.01000,0.382
196
+ 27,mlp.gate_proj,15.34180,0.01000,0.491
197
+ 27,mlp.down_proj,0.04274,0.01000,1.880
198
+ 28,self_attn.k_proj,3.10963,0.01000,0.359
199
+ 28,self_attn.v_proj,0.90080,0.01000,0.404
200
+ 28,self_attn.q_proj,8.45020,0.01000,0.422
201
+ 28,self_attn.o_proj,0.12536,0.01000,0.361
202
+ 28,mlp.up_proj,19.04866,0.01000,0.375
203
+ 28,mlp.gate_proj,24.96149,0.01000,0.435
204
+ 28,mlp.down_proj,0.12226,0.01000,1.881
205
+ 29,self_attn.k_proj,1.89022,0.01000,0.354
206
+ 29,self_attn.v_proj,0.65279,0.01000,0.353
207
+ 29,self_attn.q_proj,4.46385,0.01000,0.431
208
+ 29,self_attn.o_proj,0.01065,0.01000,0.359
209
+ 29,mlp.up_proj,15.06032,0.01000,0.380
210
+ 29,mlp.gate_proj,17.98568,0.01000,0.471
211
+ 29,mlp.down_proj,0.06156,0.01000,1.894
212
+ 30,self_attn.k_proj,3.35338,0.01000,0.360
213
+ 30,self_attn.v_proj,0.73886,0.01000,0.497
214
+ 30,self_attn.q_proj,8.27429,0.01000,0.465
215
+ 30,self_attn.o_proj,0.05691,0.01000,0.407
216
+ 30,mlp.up_proj,24.22082,0.01000,0.284
217
+ 30,mlp.gate_proj,31.44272,0.01000,0.443
218
+ 30,mlp.down_proj,0.17313,0.01000,1.368
219
+ 31,self_attn.k_proj,2.88453,0.01000,0.252
220
+ 31,self_attn.v_proj,0.61847,0.01000,0.263
221
+ 31,self_attn.q_proj,6.20819,0.01000,0.344
222
+ 31,self_attn.o_proj,0.00982,0.01000,0.255
223
+ 31,mlp.up_proj,16.11938,0.01000,0.269
224
+ 31,mlp.gate_proj,18.96483,0.01000,0.383
225
+ 31,mlp.down_proj,0.07271,0.01000,1.335
226
+ 32,self_attn.k_proj,6.66900,0.01000,0.254
227
+ 32,self_attn.v_proj,2.34639,0.01000,0.308
228
+ 32,self_attn.q_proj,15.14654,0.01000,0.251
229
+ 32,self_attn.o_proj,0.05010,0.01000,0.252
230
+ 32,mlp.up_proj,27.74219,0.01000,0.270
231
+ 32,mlp.gate_proj,42.54895,0.01000,0.384
232
+ 32,mlp.down_proj,0.29455,0.01000,1.316
233
+ 33,self_attn.k_proj,3.13420,0.01000,0.251
234
+ 33,self_attn.v_proj,1.74874,0.01000,0.267
235
+ 33,self_attn.q_proj,7.24945,0.01000,0.353
236
+ 33,self_attn.o_proj,0.01130,0.01000,0.260
237
+ 33,mlp.up_proj,20.27265,0.01000,0.265
238
+ 33,mlp.gate_proj,28.13426,0.01000,0.381
239
+ 33,mlp.down_proj,0.12377,0.01000,2.280
240
+ 34,self_attn.k_proj,3.93439,0.01000,0.251
241
+ 34,self_attn.v_proj,1.57006,0.01000,0.337
242
+ 34,self_attn.q_proj,9.14879,0.01000,0.254
243
+ 34,self_attn.o_proj,0.02188,0.01000,0.251
244
+ 34,mlp.up_proj,29.11380,0.01000,0.424
245
+ 34,mlp.gate_proj,59.26272,0.01000,0.433
246
+ 34,mlp.down_proj,0.23440,0.01000,1.326
247
+ 35,self_attn.k_proj,2.25258,0.01000,0.253
248
+ 35,self_attn.v_proj,1.03447,0.01000,0.265
249
+ 35,self_attn.q_proj,4.77424,0.01000,0.315
250
+ 35,self_attn.o_proj,0.01391,0.01000,0.251
251
+ 35,mlp.up_proj,22.42692,0.01000,0.267
252
+ 35,mlp.gate_proj,37.88570,0.01000,0.378
253
+ 35,mlp.down_proj,0.15588,0.01000,1.873
254
+ 36,self_attn.k_proj,4.07878,0.01000,0.251
255
+ 36,self_attn.v_proj,1.31110,0.01000,0.247
256
+ 36,self_attn.q_proj,9.11373,0.01000,0.336
257
+ 36,self_attn.o_proj,0.04196,0.01000,0.251
258
+ 36,mlp.up_proj,30.69535,0.01000,0.266
259
+ 36,mlp.gate_proj,48.81691,0.01000,0.374
260
+ 36,mlp.down_proj,0.24473,0.01000,1.343
261
+ 37,self_attn.k_proj,2.28196,0.01000,0.253
262
+ 37,self_attn.v_proj,0.83778,0.01000,0.307
263
+ 37,self_attn.q_proj,4.97280,0.01000,0.261
264
+ 37,self_attn.o_proj,0.03077,0.01000,0.253
265
+ 37,mlp.up_proj,25.55282,0.01000,0.274
266
+ 37,mlp.gate_proj,36.21564,0.01000,0.373
267
+ 37,mlp.down_proj,0.21938,0.01000,1.320
268
+ 38,self_attn.k_proj,3.39493,0.01000,0.252
269
+ 38,self_attn.v_proj,0.86729,0.01000,0.252
270
+ 38,self_attn.q_proj,7.32435,0.01000,0.350
271
+ 38,self_attn.o_proj,0.04364,0.01000,0.253
272
+ 38,mlp.up_proj,41.57827,0.01000,0.280
273
+ 38,mlp.gate_proj,64.67491,0.01000,0.355
274
+ 38,mlp.down_proj,0.47098,0.01000,1.334
275
+ 39,self_attn.k_proj,2.49290,0.01000,0.254
276
+ 39,self_attn.v_proj,0.90451,0.01000,0.341
277
+ 39,self_attn.q_proj,5.38168,0.01000,0.315
278
+ 39,self_attn.o_proj,0.02709,0.01000,0.252
279
+ 39,mlp.up_proj,30.90791,0.01000,0.263
280
+ 39,mlp.gate_proj,43.81223,0.01000,0.380
281
+ 39,mlp.down_proj,0.34576,0.01000,1.366
282
+ 40,self_attn.k_proj,5.68085,0.01000,0.271
283
+ 40,self_attn.v_proj,4.14036,0.01000,0.406
284
+ 40,self_attn.q_proj,11.47833,0.01000,0.331
285
+ 40,self_attn.o_proj,0.08676,0.01000,0.255
286
+ 40,mlp.up_proj,45.17474,0.01000,0.638
287
+ 40,mlp.gate_proj,66.32059,0.01000,0.600
288
+ 40,mlp.down_proj,0.69318,0.01000,1.905
289
+ 41,self_attn.k_proj,4.25041,0.01000,0.359
290
+ 41,self_attn.v_proj,2.61919,0.01000,0.433
291
+ 41,self_attn.q_proj,7.55455,0.01000,0.425
292
+ 41,self_attn.o_proj,0.03503,0.01000,0.356
293
+ 41,mlp.up_proj,37.79523,0.01000,0.376
294
+ 41,mlp.gate_proj,50.56963,0.01000,0.473
295
+ 41,mlp.down_proj,0.54696,0.01000,1.915
296
+ 42,self_attn.k_proj,7.00505,0.01000,0.356
297
+ 42,self_attn.v_proj,5.90668,0.01000,0.473
298
+ 42,self_attn.q_proj,14.50974,0.01000,0.357
299
+ 42,self_attn.o_proj,0.18478,0.01000,0.354
300
+ 42,mlp.up_proj,45.85146,0.01000,0.380
301
+ 42,mlp.gate_proj,61.16519,0.01000,0.438
302
+ 42,mlp.down_proj,1.36280,0.01000,1.929
303
+ 43,self_attn.k_proj,6.41938,0.01000,0.359
304
+ 43,self_attn.v_proj,2.73745,0.01000,0.426
305
+ 43,self_attn.q_proj,10.68003,0.01000,0.418
306
+ 43,self_attn.o_proj,0.03312,0.01000,0.363
307
+ 43,mlp.up_proj,47.07648,0.01000,0.376
308
+ 43,mlp.gate_proj,56.13808,0.01000,0.453
309
+ 43,mlp.down_proj,0.83957,0.01000,1.897
310
+ 44,self_attn.k_proj,7.83811,0.01000,0.357
311
+ 44,self_attn.v_proj,5.99721,0.01000,0.363
312
+ 44,self_attn.q_proj,15.54352,0.01000,0.418
313
+ 44,self_attn.o_proj,0.07378,0.01000,0.358
314
+ 44,mlp.up_proj,50.52370,0.01000,0.374
315
+ 44,mlp.gate_proj,56.82018,0.01000,0.483
316
+ 44,mlp.down_proj,1.07763,0.01000,1.898
317
+ 45,self_attn.k_proj,8.38010,0.01000,0.356
318
+ 45,self_attn.v_proj,3.38783,0.01000,0.417
319
+ 45,self_attn.q_proj,12.61263,0.01000,0.430
320
+ 45,self_attn.o_proj,0.05380,0.01000,0.356
321
+ 45,mlp.up_proj,51.93184,0.01000,0.367
322
+ 45,mlp.gate_proj,56.51867,0.01000,0.467
323
+ 45,mlp.down_proj,0.99369,0.01000,1.889
324
+ 46,self_attn.k_proj,9.27207,0.01000,0.359
325
+ 46,self_attn.v_proj,5.30227,0.01000,0.352
326
+ 46,self_attn.q_proj,13.91500,0.01000,0.419
327
+ 46,self_attn.o_proj,0.36553,0.01000,0.356
328
+ 46,mlp.up_proj,57.99126,0.01000,0.375
329
+ 46,mlp.gate_proj,73.99236,0.01000,0.472
330
+ 46,mlp.down_proj,1.55528,0.01000,1.936
331
+ 47,self_attn.k_proj,2.09461,0.01000,0.359
332
+ 47,self_attn.v_proj,1.72382,0.01000,0.359
333
+ 47,self_attn.q_proj,5.13000,0.01000,0.402
334
+ 47,self_attn.o_proj,0.03417,0.01000,0.366
335
+ 47,mlp.up_proj,52.20809,0.01000,0.370
336
+ 47,mlp.gate_proj,55.62090,0.01000,0.480
337
+ 47,mlp.down_proj,0.91741,0.01000,1.389
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:1.9.0"
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": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|fim_pad|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
3
+ size 11421995
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) 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{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|fim_pad|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2TokenizerFast",
207
+ "unk_token": null,
208
+ "_commit_hash": null
209
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff