jeffcookio commited on
Commit
b2b8086
·
verified ·
1 Parent(s): e5c9a7a

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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "/intnvme/models/arcee-ai/Virtuoso-Small-v2",
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "bits": 4,
21
+ "checkpoint_format": "gptq",
22
+ "desc_act": true,
23
+ "group_size": 32,
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:1.8.0-dev"
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": null,
44
+ "tie_word_embeddings": false,
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.49.0.dev0",
47
+ "use_cache": false,
48
+ "use_sliding_window": false,
49
+ "vocab_size": 151665
50
+ }
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:ea8d3ed0fb1b26ce6c536c630c91295e204fac29f2af73f310f640d23a6a42d4
3
+ size 10754733936
quant_log.csv ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,damp,time
2
+ 0,self_attn.k_proj,0.26036,0.01000,0.867
3
+ 0,self_attn.v_proj,0.05420,0.01000,0.635
4
+ 0,self_attn.q_proj,0.70063,0.01000,0.708
5
+ 0,self_attn.o_proj,0.35694,0.01000,0.712
6
+ 0,mlp.up_proj,0.30289,0.01000,0.906
7
+ 0,mlp.gate_proj,0.34156,0.01000,0.905
8
+ 0,mlp.down_proj,0.44676,0.01000,2.272
9
+ 1,self_attn.k_proj,0.00953,0.01000,0.635
10
+ 1,self_attn.v_proj,0.00322,0.01000,0.626
11
+ 1,self_attn.q_proj,0.03257,0.01000,0.711
12
+ 1,self_attn.o_proj,0.00497,0.01000,0.835
13
+ 1,mlp.up_proj,0.97963,0.01000,0.920
14
+ 1,mlp.gate_proj,2.24384,0.01000,0.935
15
+ 1,mlp.down_proj,0.06811,0.01000,2.336
16
+ 2,self_attn.k_proj,0.03853,0.01000,0.641
17
+ 2,self_attn.v_proj,0.01031,0.01000,0.639
18
+ 2,self_attn.q_proj,0.10414,0.01000,0.716
19
+ 2,self_attn.o_proj,0.03894,0.01000,0.713
20
+ 2,mlp.up_proj,2.43388,0.01000,0.926
21
+ 2,mlp.gate_proj,4.49173,0.01000,0.912
22
+ 2,mlp.down_proj,0.24585,0.01000,2.316
23
+ 3,self_attn.k_proj,0.22382,0.01000,0.650
24
+ 3,self_attn.v_proj,0.05017,0.01000,0.667
25
+ 3,self_attn.q_proj,0.60450,0.01000,0.716
26
+ 3,self_attn.o_proj,0.11714,0.01000,0.761
27
+ 3,mlp.up_proj,3.11226,0.01000,0.931
28
+ 3,mlp.gate_proj,6.43137,0.01000,0.921
29
+ 3,mlp.down_proj,0.50630,0.01000,2.279
30
+ 4,self_attn.k_proj,0.26125,0.01000,0.653
31
+ 4,self_attn.v_proj,0.08104,0.01000,0.639
32
+ 4,self_attn.q_proj,0.70841,0.01000,0.708
33
+ 4,self_attn.o_proj,0.20499,0.01000,0.707
34
+ 4,mlp.up_proj,6.60127,0.01000,0.918
35
+ 4,mlp.gate_proj,12.15986,0.01000,0.916
36
+ 4,mlp.down_proj,40.96575,0.01000,2.305
37
+ 5,self_attn.k_proj,0.92666,0.01000,0.637
38
+ 5,self_attn.v_proj,0.40086,0.01000,0.684
39
+ 5,self_attn.q_proj,2.91849,0.01000,0.762
40
+ 5,self_attn.o_proj,0.25830,0.01000,0.771
41
+ 5,mlp.up_proj,11.54552,0.01000,0.913
42
+ 5,mlp.gate_proj,22.25092,0.01000,0.917
43
+ 5,mlp.down_proj,2.16865,0.01000,2.288
44
+ 6,self_attn.k_proj,1.01429,0.01000,0.641
45
+ 6,self_attn.v_proj,0.55844,0.01000,0.651
46
+ 6,self_attn.q_proj,3.46086,0.01000,0.715
47
+ 6,self_attn.o_proj,0.24132,0.01000,0.711
48
+ 6,mlp.up_proj,18.73928,0.01000,0.930
49
+ 6,mlp.gate_proj,34.72187,0.01000,0.922
50
+ 6,mlp.down_proj,1.48732,0.01000,2.291
51
+ 7,self_attn.k_proj,1.44037,0.01000,0.646
52
+ 7,self_attn.v_proj,0.85917,0.01000,0.646
53
+ 7,self_attn.q_proj,5.06283,0.01000,0.712
54
+ 7,self_attn.o_proj,0.28499,0.01000,0.724
55
+ 7,mlp.up_proj,23.92506,0.01000,0.921
56
+ 7,mlp.gate_proj,44.41349,0.01000,0.909
57
+ 7,mlp.down_proj,1.22487,0.01000,2.322
58
+ 8,self_attn.k_proj,1.42940,0.01000,0.663
59
+ 8,self_attn.v_proj,0.65371,0.01000,0.664
60
+ 8,self_attn.q_proj,4.69804,0.01000,0.721
61
+ 8,self_attn.o_proj,0.23384,0.01000,0.718
62
+ 8,mlp.up_proj,16.61076,0.01000,0.929
63
+ 8,mlp.gate_proj,29.24774,0.01000,0.948
64
+ 8,mlp.down_proj,1.56675,0.01000,2.307
65
+ 9,self_attn.k_proj,1.35689,0.01000,0.651
66
+ 9,self_attn.v_proj,0.79814,0.01000,0.646
67
+ 9,self_attn.q_proj,4.66374,0.01000,0.718
68
+ 9,self_attn.o_proj,0.50110,0.01000,0.768
69
+ 9,mlp.up_proj,12.01456,0.01000,0.928
70
+ 9,mlp.gate_proj,13.09235,0.01000,0.925
71
+ 9,mlp.down_proj,2.41614,0.01000,2.347
72
+ 10,self_attn.k_proj,1.98604,0.01000,0.647
73
+ 10,self_attn.v_proj,1.12373,0.01000,0.652
74
+ 10,self_attn.q_proj,7.06883,0.01000,0.723
75
+ 10,self_attn.o_proj,0.44133,0.01000,0.723
76
+ 10,mlp.up_proj,13.46574,0.01000,0.909
77
+ 10,mlp.gate_proj,14.62684,0.01000,0.921
78
+ 10,mlp.down_proj,2.88275,0.01000,2.276
79
+ 11,self_attn.k_proj,1.40679,0.01000,0.658
80
+ 11,self_attn.v_proj,0.70462,0.01000,0.636
81
+ 11,self_attn.q_proj,4.87083,0.01000,0.709
82
+ 11,self_attn.o_proj,0.73486,0.01000,0.730
83
+ 11,mlp.up_proj,15.24331,0.01000,0.901
84
+ 11,mlp.gate_proj,18.96236,0.01000,0.909
85
+ 11,mlp.down_proj,2.67517,0.01000,2.278
86
+ 12,self_attn.k_proj,1.75421,0.01000,0.651
87
+ 12,self_attn.v_proj,0.84060,0.01000,0.635
88
+ 12,self_attn.q_proj,6.15144,0.01000,0.708
89
+ 12,self_attn.o_proj,0.77835,0.01000,0.707
90
+ 12,mlp.up_proj,16.70987,0.01000,0.905
91
+ 12,mlp.gate_proj,17.71281,0.01000,0.904
92
+ 12,mlp.down_proj,3.27058,0.01000,2.282
93
+ 13,self_attn.k_proj,1.89015,0.01000,0.643
94
+ 13,self_attn.v_proj,1.01020,0.01000,0.643
95
+ 13,self_attn.q_proj,6.54569,0.01000,0.711
96
+ 13,self_attn.o_proj,0.86889,0.01000,0.711
97
+ 13,mlp.up_proj,18.78529,0.01000,0.920
98
+ 13,mlp.gate_proj,19.94199,0.01000,0.916
99
+ 13,mlp.down_proj,3.72944,0.01000,2.284
100
+ 14,self_attn.k_proj,2.30529,0.01000,0.654
101
+ 14,self_attn.v_proj,1.12327,0.01000,0.636
102
+ 14,self_attn.q_proj,7.94638,0.01000,0.706
103
+ 14,self_attn.o_proj,0.92339,0.01000,0.710
104
+ 14,mlp.up_proj,19.09062,0.01000,0.916
105
+ 14,mlp.gate_proj,20.10281,0.01000,0.915
106
+ 14,mlp.down_proj,3.95867,0.01000,2.288
107
+ 15,self_attn.k_proj,1.97048,0.01000,0.644
108
+ 15,self_attn.v_proj,1.26913,0.01000,0.637
109
+ 15,self_attn.q_proj,7.20539,0.01000,0.705
110
+ 15,self_attn.o_proj,1.15352,0.01000,0.713
111
+ 15,mlp.up_proj,19.46122,0.01000,0.916
112
+ 15,mlp.gate_proj,21.46150,0.01000,0.910
113
+ 15,mlp.down_proj,4.03750,0.01000,2.296
114
+ 16,self_attn.k_proj,1.95918,0.01000,0.650
115
+ 16,self_attn.v_proj,0.83442,0.01000,0.642
116
+ 16,self_attn.q_proj,6.19330,0.01000,0.719
117
+ 16,self_attn.o_proj,0.95438,0.01000,0.714
118
+ 16,mlp.up_proj,17.69310,0.01000,0.917
119
+ 16,mlp.gate_proj,17.95339,0.01000,0.927
120
+ 16,mlp.down_proj,3.89098,0.01000,2.293
121
+ 17,self_attn.k_proj,2.14327,0.01000,0.641
122
+ 17,self_attn.v_proj,0.96848,0.01000,0.637
123
+ 17,self_attn.q_proj,7.31796,0.01000,0.703
124
+ 17,self_attn.o_proj,0.96067,0.01000,0.721
125
+ 17,mlp.up_proj,17.25422,0.01000,0.905
126
+ 17,mlp.gate_proj,17.00942,0.01000,0.905
127
+ 17,mlp.down_proj,3.66447,0.01000,2.437
128
+ 18,self_attn.k_proj,2.05424,0.01000,0.654
129
+ 18,self_attn.v_proj,1.05943,0.01000,0.691
130
+ 18,self_attn.q_proj,7.09151,0.01000,0.712
131
+ 18,self_attn.o_proj,1.15249,0.01000,0.716
132
+ 18,mlp.up_proj,17.08627,0.01000,0.941
133
+ 18,mlp.gate_proj,16.31715,0.01000,0.934
134
+ 18,mlp.down_proj,3.64738,0.01000,2.328
135
+ 19,self_attn.k_proj,2.23101,0.01000,0.729
136
+ 19,self_attn.v_proj,1.12143,0.01000,0.688
137
+ 19,self_attn.q_proj,8.30859,0.01000,0.721
138
+ 19,self_attn.o_proj,0.85230,0.01000,0.723
139
+ 19,mlp.up_proj,17.57046,0.01000,0.915
140
+ 19,mlp.gate_proj,16.74862,0.01000,0.914
141
+ 19,mlp.down_proj,3.70768,0.01000,3.234
142
+ 20,self_attn.k_proj,2.31831,0.01000,0.644
143
+ 20,self_attn.v_proj,1.01319,0.01000,0.640
144
+ 20,self_attn.q_proj,8.01723,0.01000,0.707
145
+ 20,self_attn.o_proj,1.11558,0.01000,0.715
146
+ 20,mlp.up_proj,16.66207,0.01000,0.898
147
+ 20,mlp.gate_proj,15.08692,0.01000,0.917
148
+ 20,mlp.down_proj,3.63861,0.01000,2.293
149
+ 21,self_attn.k_proj,2.12553,0.01000,0.676
150
+ 21,self_attn.v_proj,0.99634,0.01000,0.634
151
+ 21,self_attn.q_proj,7.33409,0.01000,0.697
152
+ 21,self_attn.o_proj,1.09183,0.01000,0.700
153
+ 21,mlp.up_proj,16.34967,0.01000,0.897
154
+ 21,mlp.gate_proj,14.69851,0.01000,0.905
155
+ 21,mlp.down_proj,3.35195,0.01000,2.259
156
+ 22,self_attn.k_proj,2.30831,0.01000,0.637
157
+ 22,self_attn.v_proj,1.41462,0.01000,0.630
158
+ 22,self_attn.q_proj,8.18642,0.01000,0.691
159
+ 22,self_attn.o_proj,1.24221,0.01000,0.700
160
+ 22,mlp.up_proj,16.62011,0.01000,0.887
161
+ 22,mlp.gate_proj,14.80098,0.01000,0.895
162
+ 22,mlp.down_proj,3.48646,0.01000,2.254
163
+ 23,self_attn.k_proj,2.21277,0.01000,0.638
164
+ 23,self_attn.v_proj,1.49767,0.01000,0.633
165
+ 23,self_attn.q_proj,8.29903,0.01000,0.692
166
+ 23,self_attn.o_proj,1.34244,0.01000,0.696
167
+ 23,mlp.up_proj,16.86485,0.01000,0.925
168
+ 23,mlp.gate_proj,15.79704,0.01000,0.921
169
+ 23,mlp.down_proj,3.57027,0.01000,2.292
170
+ 24,self_attn.k_proj,2.82373,0.01000,0.638
171
+ 24,self_attn.v_proj,1.25355,0.01000,0.648
172
+ 24,self_attn.q_proj,9.15804,0.01000,0.766
173
+ 24,self_attn.o_proj,1.35876,0.01000,0.739
174
+ 24,mlp.up_proj,16.41576,0.01000,0.905
175
+ 24,mlp.gate_proj,15.28884,0.01000,0.902
176
+ 24,mlp.down_proj,3.43679,0.01000,2.274
177
+ 25,self_attn.k_proj,2.85689,0.01000,0.645
178
+ 25,self_attn.v_proj,1.56041,0.01000,0.643
179
+ 25,self_attn.q_proj,10.26073,0.01000,0.705
180
+ 25,self_attn.o_proj,0.96909,0.01000,0.727
181
+ 25,mlp.up_proj,17.04817,0.01000,0.936
182
+ 25,mlp.gate_proj,15.29261,0.01000,0.928
183
+ 25,mlp.down_proj,3.83192,0.01000,2.366
184
+ 26,self_attn.k_proj,2.59108,0.01000,0.656
185
+ 26,self_attn.v_proj,1.13437,0.01000,0.653
186
+ 26,self_attn.q_proj,9.02508,0.01000,0.705
187
+ 26,self_attn.o_proj,1.18537,0.01000,0.704
188
+ 26,mlp.up_proj,18.28733,0.01000,0.904
189
+ 26,mlp.gate_proj,15.66199,0.01000,0.898
190
+ 26,mlp.down_proj,4.31631,0.01000,2.369
191
+ 27,self_attn.k_proj,2.75956,0.01000,0.661
192
+ 27,self_attn.v_proj,1.40736,0.01000,0.659
193
+ 27,self_attn.q_proj,9.25604,0.01000,0.742
194
+ 27,self_attn.o_proj,1.72676,0.01000,0.741
195
+ 27,mlp.up_proj,19.44541,0.01000,0.913
196
+ 27,mlp.gate_proj,16.41549,0.01000,0.900
197
+ 27,mlp.down_proj,4.96648,0.01000,2.288
198
+ 28,self_attn.k_proj,2.31360,0.01000,0.637
199
+ 28,self_attn.v_proj,2.04337,0.01000,0.639
200
+ 28,self_attn.q_proj,9.41305,0.01000,0.706
201
+ 28,self_attn.o_proj,1.94308,0.01000,0.707
202
+ 28,mlp.up_proj,19.80026,0.01000,0.915
203
+ 28,mlp.gate_proj,16.55652,0.01000,0.899
204
+ 28,mlp.down_proj,5.40219,0.01000,2.278
205
+ 29,self_attn.k_proj,2.88307,0.01000,0.635
206
+ 29,self_attn.v_proj,2.04302,0.01000,0.641
207
+ 29,self_attn.q_proj,10.79088,0.01000,0.704
208
+ 29,self_attn.o_proj,1.94909,0.01000,0.704
209
+ 29,mlp.up_proj,20.19841,0.01000,0.902
210
+ 29,mlp.gate_proj,16.93391,0.01000,0.893
211
+ 29,mlp.down_proj,5.92107,0.01000,2.267
212
+ 30,self_attn.k_proj,2.58491,0.01000,0.634
213
+ 30,self_attn.v_proj,2.15580,0.01000,0.645
214
+ 30,self_attn.q_proj,10.09076,0.01000,0.702
215
+ 30,self_attn.o_proj,2.59414,0.01000,0.714
216
+ 30,mlp.up_proj,20.44093,0.01000,0.894
217
+ 30,mlp.gate_proj,17.29723,0.01000,0.892
218
+ 30,mlp.down_proj,6.64402,0.01000,2.281
219
+ 31,self_attn.k_proj,2.57551,0.01000,0.639
220
+ 31,self_attn.v_proj,2.12479,0.01000,0.631
221
+ 31,self_attn.q_proj,10.04355,0.01000,0.698
222
+ 31,self_attn.o_proj,2.31283,0.01000,0.699
223
+ 31,mlp.up_proj,22.42635,0.01000,0.888
224
+ 31,mlp.gate_proj,19.47521,0.01000,0.896
225
+ 31,mlp.down_proj,7.99958,0.01000,2.255
226
+ 32,self_attn.k_proj,2.75304,0.01000,0.640
227
+ 32,self_attn.v_proj,2.64117,0.01000,0.631
228
+ 32,self_attn.q_proj,10.68653,0.01000,0.691
229
+ 32,self_attn.o_proj,2.25520,0.01000,0.697
230
+ 32,mlp.up_proj,24.00047,0.01000,0.890
231
+ 32,mlp.gate_proj,21.39172,0.01000,0.883
232
+ 32,mlp.down_proj,9.30199,0.01000,2.261
233
+ 33,self_attn.k_proj,2.85051,0.01000,0.630
234
+ 33,self_attn.v_proj,2.67928,0.01000,0.631
235
+ 33,self_attn.q_proj,11.52042,0.01000,0.696
236
+ 33,self_attn.o_proj,2.73352,0.01000,0.703
237
+ 33,mlp.up_proj,28.60492,0.01000,0.883
238
+ 33,mlp.gate_proj,25.90147,0.01000,0.889
239
+ 33,mlp.down_proj,13.51039,0.01000,2.277
240
+ 34,self_attn.k_proj,2.94382,0.01000,0.637
241
+ 34,self_attn.v_proj,3.15674,0.01000,0.631
242
+ 34,self_attn.q_proj,12.46972,0.01000,0.695
243
+ 34,self_attn.o_proj,2.24677,0.01000,0.695
244
+ 34,mlp.up_proj,32.94138,0.01000,0.887
245
+ 34,mlp.gate_proj,30.67356,0.01000,0.884
246
+ 34,mlp.down_proj,16.44095,0.01000,2.240
247
+ 35,self_attn.k_proj,2.82023,0.01000,0.633
248
+ 35,self_attn.v_proj,2.72677,0.01000,0.627
249
+ 35,self_attn.q_proj,11.21398,0.01000,0.701
250
+ 35,self_attn.o_proj,4.09978,0.01000,0.719
251
+ 35,mlp.up_proj,37.04214,0.01000,0.892
252
+ 35,mlp.gate_proj,35.36028,0.01000,0.885
253
+ 35,mlp.down_proj,20.64363,0.01000,2.249
254
+ 36,self_attn.k_proj,3.12526,0.01000,0.639
255
+ 36,self_attn.v_proj,4.86601,0.01000,0.636
256
+ 36,self_attn.q_proj,13.88613,0.01000,0.701
257
+ 36,self_attn.o_proj,3.32567,0.01000,0.698
258
+ 36,mlp.up_proj,40.51837,0.01000,0.894
259
+ 36,mlp.gate_proj,38.31907,0.01000,0.885
260
+ 36,mlp.down_proj,25.58770,0.01000,2.253
261
+ 37,self_attn.k_proj,3.48153,0.01000,0.640
262
+ 37,self_attn.v_proj,4.82382,0.01000,0.633
263
+ 37,self_attn.q_proj,13.99707,0.01000,0.692
264
+ 37,self_attn.o_proj,4.31657,0.01000,0.702
265
+ 37,mlp.up_proj,45.02293,0.01000,0.889
266
+ 37,mlp.gate_proj,42.76265,0.01000,0.887
267
+ 37,mlp.down_proj,29.33503,0.01000,2.246
268
+ 38,self_attn.k_proj,3.36857,0.01000,0.634
269
+ 38,self_attn.v_proj,4.76479,0.01000,0.636
270
+ 38,self_attn.q_proj,14.21926,0.01000,0.697
271
+ 38,self_attn.o_proj,4.08717,0.01000,0.702
272
+ 38,mlp.up_proj,50.84389,0.01000,0.895
273
+ 38,mlp.gate_proj,47.83739,0.01000,0.887
274
+ 38,mlp.down_proj,34.10911,0.01000,2.248
275
+ 39,self_attn.k_proj,3.25492,0.01000,0.641
276
+ 39,self_attn.v_proj,5.25485,0.01000,0.629
277
+ 39,self_attn.q_proj,14.65375,0.01000,0.696
278
+ 39,self_attn.o_proj,5.51222,0.01000,0.697
279
+ 39,mlp.up_proj,56.42299,0.01000,0.885
280
+ 39,mlp.gate_proj,52.54479,0.01000,0.886
281
+ 39,mlp.down_proj,41.12865,0.01000,2.254
282
+ 40,self_attn.k_proj,3.57945,0.01000,0.641
283
+ 40,self_attn.v_proj,7.09772,0.01000,0.635
284
+ 40,self_attn.q_proj,15.55286,0.01000,0.698
285
+ 40,self_attn.o_proj,4.64640,0.01000,0.706
286
+ 40,mlp.up_proj,61.18236,0.01000,0.889
287
+ 40,mlp.gate_proj,56.57283,0.01000,0.901
288
+ 40,mlp.down_proj,47.88690,0.01000,2.257
289
+ 41,self_attn.k_proj,3.49766,0.01000,0.636
290
+ 41,self_attn.v_proj,7.51067,0.01000,0.628
291
+ 41,self_attn.q_proj,16.35394,0.01000,0.693
292
+ 41,self_attn.o_proj,4.47999,0.01000,0.696
293
+ 41,mlp.up_proj,67.32155,0.01000,0.888
294
+ 41,mlp.gate_proj,61.51566,0.01000,0.891
295
+ 41,mlp.down_proj,56.35289,0.01000,2.274
296
+ 42,self_attn.k_proj,3.63002,0.01000,0.647
297
+ 42,self_attn.v_proj,8.31092,0.01000,0.639
298
+ 42,self_attn.q_proj,15.66547,0.01000,0.724
299
+ 42,self_attn.o_proj,4.55145,0.01000,0.712
300
+ 42,mlp.up_proj,74.24236,0.01000,0.899
301
+ 42,mlp.gate_proj,66.90302,0.01000,0.893
302
+ 42,mlp.down_proj,68.06916,0.01000,2.253
303
+ 43,self_attn.k_proj,3.66244,0.01000,0.652
304
+ 43,self_attn.v_proj,12.12363,0.01000,0.637
305
+ 43,self_attn.q_proj,17.61745,0.01000,0.697
306
+ 43,self_attn.o_proj,8.88469,0.01000,0.704
307
+ 43,mlp.up_proj,83.69629,0.01000,0.909
308
+ 43,mlp.gate_proj,73.91648,0.01000,0.893
309
+ 43,mlp.down_proj,85.75832,0.01000,2.255
310
+ 44,self_attn.k_proj,3.44381,0.01000,0.639
311
+ 44,self_attn.v_proj,13.53937,0.01000,0.632
312
+ 44,self_attn.q_proj,17.71445,0.01000,0.697
313
+ 44,self_attn.o_proj,14.18654,0.01000,0.702
314
+ 44,mlp.up_proj,89.77986,0.01000,0.888
315
+ 44,mlp.gate_proj,77.92497,0.01000,0.887
316
+ 44,mlp.down_proj,126.31661,0.01000,2.258
317
+ 45,self_attn.k_proj,3.54014,0.01000,0.640
318
+ 45,self_attn.v_proj,17.02522,0.01000,0.634
319
+ 45,self_attn.q_proj,18.31204,0.01000,0.698
320
+ 45,self_attn.o_proj,13.89032,0.01000,0.708
321
+ 45,mlp.up_proj,96.09402,0.01000,0.894
322
+ 45,mlp.gate_proj,84.49706,0.01000,0.893
323
+ 45,mlp.down_proj,141.59793,0.01000,2.291
324
+ 46,self_attn.k_proj,3.35453,0.01000,0.663
325
+ 46,self_attn.v_proj,19.15645,0.01000,0.636
326
+ 46,self_attn.q_proj,17.69115,0.01000,0.700
327
+ 46,self_attn.o_proj,25.01622,0.01000,0.701
328
+ 46,mlp.up_proj,96.24874,0.01000,0.892
329
+ 46,mlp.gate_proj,88.16650,0.01000,0.896
330
+ 46,mlp.down_proj,179.22986,0.01000,2.243
331
+ 47,self_attn.k_proj,3.00164,0.01000,0.640
332
+ 47,self_attn.v_proj,11.63318,0.01000,0.644
333
+ 47,self_attn.q_proj,13.82666,0.01000,0.693
334
+ 47,self_attn.o_proj,11.58855,0.01000,0.704
335
+ 47,mlp.up_proj,101.07446,0.01000,0.886
336
+ 47,mlp.gate_proj,95.90570,0.01000,0.885
337
+ 47,mlp.down_proj,241.01828,0.01000,2.254
quantize_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 32,
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:1.8.0-dev"
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
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 Virtuoso Small, created by Arcee AI. 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 Qwen, created by Alibaba Cloud. You 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": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<unk>",
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