wolfofbackstreet commited on
Commit
a6baa9c
·
verified ·
1 Parent(s): 15a8611

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
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 48,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 151643,
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:3.0.0-dev"
31
+ ],
32
+ "static_groups": false,
33
+ "true_sequential": true,
34
+ "uri": "https://github.com/modelcloud/gptqmodel",
35
+ "v2": false,
36
+ "v2_alpha": 0.25
37
+ },
38
+ "pack_dtype": "int32",
39
+ "quant_method": "gptq",
40
+ "sym": true
41
+ },
42
+ "rms_norm_eps": 1e-05,
43
+ "rope_scaling": null,
44
+ "rope_theta": 1000000.0,
45
+ "sliding_window": null,
46
+ "tie_word_embeddings": false,
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.51.3",
49
+ "use_cache": true,
50
+ "use_sliding_window": false,
51
+ "vocab_size": 152064
52
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.51.3"
9
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a20635b3d117c445ed1478f07f1806ab084862bc98ca7ad140387aa809b528
3
+ size 3991846296
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e784dcc8a767655f3d8d67ec16aebf83aa63b8dfc260b24dbea1e33412189c1
3
+ size 3973264384
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5668af18cfa0d9ee91c4f11855fff34d60e5db7cc24b21295ecf30f98009413f
3
+ size 2023648928
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quant_log.csv ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.0000002985,0.01000,4.947
3
+ 0,self_attn.v_proj,0.0000000628,0.01000,1.884
4
+ 0,self_attn.q_proj,0.0000008087,0.01000,1.865
5
+ 0,self_attn.o_proj,0.0000009411,0.01000,1.889
6
+ 0,mlp.up_proj,0.0000003857,0.01000,1.936
7
+ 0,mlp.gate_proj,0.0000004343,0.01000,1.944
8
+ 0,mlp.down_proj,0.0000008139,0.01000,6.115
9
+ 1,self_attn.k_proj,0.0000000138,0.01000,1.904
10
+ 1,self_attn.v_proj,0.0000000049,0.01000,1.858
11
+ 1,self_attn.q_proj,0.0000000554,0.01000,1.897
12
+ 1,self_attn.o_proj,0.0000000136,0.01000,1.902
13
+ 1,mlp.up_proj,0.0000018059,0.01000,1.992
14
+ 1,mlp.gate_proj,0.0000048088,0.01000,1.986
15
+ 1,mlp.down_proj,0.0000000962,0.01000,6.180
16
+ 2,self_attn.k_proj,0.0000000607,0.01000,1.859
17
+ 2,self_attn.v_proj,0.0000000150,0.01000,1.884
18
+ 2,self_attn.q_proj,0.0000001718,0.01000,1.890
19
+ 2,self_attn.o_proj,0.0000000996,0.01000,1.952
20
+ 2,mlp.up_proj,0.0000043320,0.01000,2.028
21
+ 2,mlp.gate_proj,0.0000081417,0.01000,1.956
22
+ 2,mlp.down_proj,0.0000004419,0.01000,6.144
23
+ 3,self_attn.k_proj,0.0000003379,0.01000,1.877
24
+ 3,self_attn.v_proj,0.0000000693,0.01000,1.870
25
+ 3,self_attn.q_proj,0.0000009042,0.01000,1.892
26
+ 3,self_attn.o_proj,0.0000002491,0.01000,1.931
27
+ 3,mlp.up_proj,0.0000050404,0.01000,1.994
28
+ 3,mlp.gate_proj,0.0000106641,0.01000,1.996
29
+ 3,mlp.down_proj,0.0000007892,0.01000,6.105
30
+ 4,self_attn.k_proj,0.0000003962,0.01000,1.884
31
+ 4,self_attn.v_proj,0.0000001156,0.01000,1.823
32
+ 4,self_attn.q_proj,0.0000010681,0.01000,1.846
33
+ 4,self_attn.o_proj,0.0000004779,0.01000,1.910
34
+ 4,mlp.up_proj,0.0000107675,0.01000,2.053
35
+ 4,mlp.gate_proj,0.0000199058,0.01000,2.028
36
+ 4,mlp.down_proj,0.0013483506,0.01000,6.148
37
+ 5,self_attn.k_proj,0.0000013836,0.01000,1.869
38
+ 5,self_attn.v_proj,0.0000005688,0.01000,1.827
39
+ 5,self_attn.q_proj,0.0000044049,0.01000,1.926
40
+ 5,self_attn.o_proj,0.0000007381,0.01000,1.906
41
+ 5,mlp.up_proj,0.0000180994,0.01000,1.995
42
+ 5,mlp.gate_proj,0.0000349824,0.01000,1.990
43
+ 5,mlp.down_proj,0.0000037041,0.01000,6.229
44
+ 6,self_attn.k_proj,0.0000015295,0.01000,1.891
45
+ 6,self_attn.v_proj,0.0000008116,0.01000,1.841
46
+ 6,self_attn.q_proj,0.0000052489,0.01000,1.904
47
+ 6,self_attn.o_proj,0.0000006595,0.01000,1.914
48
+ 6,mlp.up_proj,0.0000294027,0.01000,2.036
49
+ 6,mlp.gate_proj,0.0000543190,0.01000,2.000
50
+ 6,mlp.down_proj,0.0000033944,0.01000,6.185
51
+ 7,self_attn.k_proj,0.0000022324,0.01000,1.848
52
+ 7,self_attn.v_proj,0.0000012807,0.01000,1.836
53
+ 7,self_attn.q_proj,0.0000077740,0.01000,1.898
54
+ 7,self_attn.o_proj,0.0000006588,0.01000,1.889
55
+ 7,mlp.up_proj,0.0000377604,0.01000,2.007
56
+ 7,mlp.gate_proj,0.0000714821,0.01000,2.013
57
+ 7,mlp.down_proj,0.0000025652,0.01000,6.107
58
+ 8,self_attn.k_proj,0.0000024254,0.01000,1.863
59
+ 8,self_attn.v_proj,0.0000010471,0.01000,1.841
60
+ 8,self_attn.q_proj,0.0000081145,0.01000,1.936
61
+ 8,self_attn.o_proj,0.0000005655,0.01000,1.886
62
+ 8,mlp.up_proj,0.0000263257,0.01000,2.090
63
+ 8,mlp.gate_proj,0.0000475203,0.01000,2.009
64
+ 8,mlp.down_proj,0.0000034082,0.01000,6.117
65
+ 9,self_attn.k_proj,0.0000022917,0.01000,1.865
66
+ 9,self_attn.v_proj,0.0000013029,0.01000,1.832
67
+ 9,self_attn.q_proj,0.0000077636,0.01000,1.919
68
+ 9,self_attn.o_proj,0.0000010365,0.01000,1.908
69
+ 9,mlp.up_proj,0.0000193074,0.01000,1.997
70
+ 9,mlp.gate_proj,0.0000211020,0.01000,2.014
71
+ 9,mlp.down_proj,0.0000048219,0.01000,6.151
72
+ 10,self_attn.k_proj,0.0000034324,0.01000,1.867
73
+ 10,self_attn.v_proj,0.0000019137,0.01000,1.831
74
+ 10,self_attn.q_proj,0.0000121056,0.01000,1.897
75
+ 10,self_attn.o_proj,0.0000010023,0.01000,1.873
76
+ 10,mlp.up_proj,0.0000224903,0.01000,2.013
77
+ 10,mlp.gate_proj,0.0000246599,0.01000,2.011
78
+ 10,mlp.down_proj,0.0000059849,0.01000,6.103
79
+ 11,self_attn.k_proj,0.0000025495,0.01000,1.908
80
+ 11,self_attn.v_proj,0.0000012462,0.01000,1.865
81
+ 11,self_attn.q_proj,0.0000090048,0.01000,1.923
82
+ 11,self_attn.o_proj,0.0000014718,0.01000,1.924
83
+ 11,mlp.up_proj,0.0000258469,0.01000,2.027
84
+ 11,mlp.gate_proj,0.0000321958,0.01000,1.986
85
+ 11,mlp.down_proj,0.0000051555,0.01000,6.087
86
+ 12,self_attn.k_proj,0.0000031215,0.01000,1.847
87
+ 12,self_attn.v_proj,0.0000014327,0.01000,1.841
88
+ 12,self_attn.q_proj,0.0000111406,0.01000,1.893
89
+ 12,self_attn.o_proj,0.0000017573,0.01000,1.957
90
+ 12,mlp.up_proj,0.0000284193,0.01000,2.017
91
+ 12,mlp.gate_proj,0.0000301645,0.01000,1.993
92
+ 12,mlp.down_proj,0.0000064959,0.01000,6.090
93
+ 13,self_attn.k_proj,0.0000034285,0.01000,1.923
94
+ 13,self_attn.v_proj,0.0000017783,0.01000,1.831
95
+ 13,self_attn.q_proj,0.0000119425,0.01000,1.911
96
+ 13,self_attn.o_proj,0.0000020312,0.01000,1.861
97
+ 13,mlp.up_proj,0.0000325586,0.01000,2.011
98
+ 13,mlp.gate_proj,0.0000345637,0.01000,1.978
99
+ 13,mlp.down_proj,0.0000076320,0.01000,6.090
100
+ 14,self_attn.k_proj,0.0000042219,0.01000,1.872
101
+ 14,self_attn.v_proj,0.0000019629,0.01000,1.827
102
+ 14,self_attn.q_proj,0.0000144176,0.01000,1.895
103
+ 14,self_attn.o_proj,0.0000020731,0.01000,1.931
104
+ 14,mlp.up_proj,0.0000335783,0.01000,2.019
105
+ 14,mlp.gate_proj,0.0000354549,0.01000,2.017
106
+ 14,mlp.down_proj,0.0000079941,0.01000,6.158
107
+ 15,self_attn.k_proj,0.0000036243,0.01000,1.894
108
+ 15,self_attn.v_proj,0.0000022559,0.01000,1.827
109
+ 15,self_attn.q_proj,0.0000129040,0.01000,1.897
110
+ 15,self_attn.o_proj,0.0000027518,0.01000,1.912
111
+ 15,mlp.up_proj,0.0000350510,0.01000,2.121
112
+ 15,mlp.gate_proj,0.0000385737,0.01000,1.996
113
+ 15,mlp.down_proj,0.0000085556,0.01000,6.094
114
+ 16,self_attn.k_proj,0.0000036654,0.01000,1.849
115
+ 16,self_attn.v_proj,0.0000015336,0.01000,1.822
116
+ 16,self_attn.q_proj,0.0000115880,0.01000,1.872
117
+ 16,self_attn.o_proj,0.0000024392,0.01000,1.921
118
+ 16,mlp.up_proj,0.0000326376,0.01000,2.085
119
+ 16,mlp.gate_proj,0.0000331992,0.01000,2.003
120
+ 16,mlp.down_proj,0.0000084625,0.01000,6.173
121
+ 17,self_attn.k_proj,0.0000040579,0.01000,1.885
122
+ 17,self_attn.v_proj,0.0000018465,0.01000,1.861
123
+ 17,self_attn.q_proj,0.0000138158,0.01000,1.906
124
+ 17,self_attn.o_proj,0.0000025808,0.01000,1.932
125
+ 17,mlp.up_proj,0.0000322729,0.01000,2.001
126
+ 17,mlp.gate_proj,0.0000317870,0.01000,1.997
127
+ 17,mlp.down_proj,0.0000080485,0.01000,6.129
128
+ 18,self_attn.k_proj,0.0000039598,0.01000,1.839
129
+ 18,self_attn.v_proj,0.0000020382,0.01000,1.798
130
+ 18,self_attn.q_proj,0.0000137095,0.01000,1.895
131
+ 18,self_attn.o_proj,0.0000029167,0.01000,1.892
132
+ 18,mlp.up_proj,0.0000323423,0.01000,1.998
133
+ 18,mlp.gate_proj,0.0000308571,0.01000,2.011
134
+ 18,mlp.down_proj,0.0000081186,0.01000,6.181
135
+ 19,self_attn.k_proj,0.0000043350,0.01000,1.867
136
+ 19,self_attn.v_proj,0.0000020963,0.01000,1.811
137
+ 19,self_attn.q_proj,0.0000163849,0.01000,1.886
138
+ 19,self_attn.o_proj,0.0000022194,0.01000,1.976
139
+ 19,mlp.up_proj,0.0000333286,0.01000,2.074
140
+ 19,mlp.gate_proj,0.0000317924,0.01000,2.042
141
+ 19,mlp.down_proj,0.0000083289,0.01000,6.124
142
+ 20,self_attn.k_proj,0.0000045548,0.01000,1.827
143
+ 20,self_attn.v_proj,0.0000019402,0.01000,1.863
144
+ 20,self_attn.q_proj,0.0000157211,0.01000,1.926
145
+ 20,self_attn.o_proj,0.0000029912,0.01000,1.890
146
+ 20,mlp.up_proj,0.0000323250,0.01000,2.020
147
+ 20,mlp.gate_proj,0.0000292523,0.01000,1.999
148
+ 20,mlp.down_proj,0.0000087532,0.01000,6.119
149
+ 21,self_attn.k_proj,0.0000042023,0.01000,1.894
150
+ 21,self_attn.v_proj,0.0000019321,0.01000,1.853
151
+ 21,self_attn.q_proj,0.0000144628,0.01000,1.918
152
+ 21,self_attn.o_proj,0.0000030416,0.01000,1.891
153
+ 21,mlp.up_proj,0.0000326811,0.01000,1.994
154
+ 21,mlp.gate_proj,0.0000293238,0.01000,1.979
155
+ 21,mlp.down_proj,0.0000085412,0.01000,6.151
156
+ 22,self_attn.k_proj,0.0000046789,0.01000,1.887
157
+ 22,self_attn.v_proj,0.0000028668,0.01000,1.833
158
+ 22,self_attn.q_proj,0.0000161835,0.01000,1.896
159
+ 22,self_attn.o_proj,0.0000038789,0.01000,1.901
160
+ 22,mlp.up_proj,0.0000331632,0.01000,2.071
161
+ 22,mlp.gate_proj,0.0000295798,0.01000,1.978
162
+ 22,mlp.down_proj,0.0000096156,0.01000,6.178
163
+ 23,self_attn.k_proj,0.0000043162,0.01000,1.860
164
+ 23,self_attn.v_proj,0.0000028849,0.01000,1.833
165
+ 23,self_attn.q_proj,0.0000160021,0.01000,1.861
166
+ 23,self_attn.o_proj,0.0000037945,0.01000,1.923
167
+ 23,mlp.up_proj,0.0000337720,0.01000,2.003
168
+ 23,mlp.gate_proj,0.0000317463,0.01000,2.011
169
+ 23,mlp.down_proj,0.0000093671,0.01000,6.194
170
+ 24,self_attn.k_proj,0.0000057187,0.01000,1.942
171
+ 24,self_attn.v_proj,0.0000024407,0.01000,1.866
172
+ 24,self_attn.q_proj,0.0000181873,0.01000,1.904
173
+ 24,self_attn.o_proj,0.0000041032,0.01000,1.924
174
+ 24,mlp.up_proj,0.0000324691,0.01000,2.000
175
+ 24,mlp.gate_proj,0.0000301167,0.01000,1.985
176
+ 24,mlp.down_proj,0.0000084492,0.01000,6.136
177
+ 25,self_attn.k_proj,0.0000055621,0.01000,1.846
178
+ 25,self_attn.v_proj,0.0000031424,0.01000,1.823
179
+ 25,self_attn.q_proj,0.0000198023,0.01000,1.922
180
+ 25,self_attn.o_proj,0.0000028802,0.01000,1.885
181
+ 25,mlp.up_proj,0.0000330885,0.01000,2.068
182
+ 25,mlp.gate_proj,0.0000296588,0.01000,2.031
183
+ 25,mlp.down_proj,0.0000089875,0.01000,6.062
184
+ 26,self_attn.k_proj,0.0000050286,0.01000,1.858
185
+ 26,self_attn.v_proj,0.0000021552,0.01000,1.866
186
+ 26,self_attn.q_proj,0.0000176642,0.01000,1.899
187
+ 26,self_attn.o_proj,0.0000031027,0.01000,1.904
188
+ 26,mlp.up_proj,0.0000356900,0.01000,2.014
189
+ 26,mlp.gate_proj,0.0000308428,0.01000,1.988
190
+ 26,mlp.down_proj,0.0000103464,0.01000,6.112
191
+ 27,self_attn.k_proj,0.0000050559,0.01000,1.826
192
+ 27,self_attn.v_proj,0.0000026083,0.01000,1.817
193
+ 27,self_attn.q_proj,0.0000170910,0.01000,1.898
194
+ 27,self_attn.o_proj,0.0000044997,0.01000,1.891
195
+ 27,mlp.up_proj,0.0000373241,0.01000,2.002
196
+ 27,mlp.gate_proj,0.0000323265,0.01000,2.026
197
+ 27,mlp.down_proj,0.0000123207,0.01000,6.172
198
+ 28,self_attn.k_proj,0.0000042150,0.01000,1.883
199
+ 28,self_attn.v_proj,0.0000037593,0.01000,1.861
200
+ 28,self_attn.q_proj,0.0000171301,0.01000,1.885
201
+ 28,self_attn.o_proj,0.0000054424,0.01000,1.916
202
+ 28,mlp.up_proj,0.0000382802,0.01000,1.990
203
+ 28,mlp.gate_proj,0.0000329041,0.01000,2.059
204
+ 28,mlp.down_proj,0.0000136056,0.01000,6.099
205
+ 29,self_attn.k_proj,0.0000055420,0.01000,1.847
206
+ 29,self_attn.v_proj,0.0000036558,0.01000,1.942
207
+ 29,self_attn.q_proj,0.0000196112,0.01000,1.991
208
+ 29,self_attn.o_proj,0.0000046135,0.01000,1.879
209
+ 29,mlp.up_proj,0.0000391342,0.01000,2.033
210
+ 29,mlp.gate_proj,0.0000337284,0.01000,1.968
211
+ 29,mlp.down_proj,0.0000148448,0.01000,6.136
212
+ 30,self_attn.k_proj,0.0000047346,0.01000,1.847
213
+ 30,self_attn.v_proj,0.0000041514,0.01000,1.863
214
+ 30,self_attn.q_proj,0.0000184229,0.01000,1.959
215
+ 30,self_attn.o_proj,0.0000064813,0.01000,1.855
216
+ 30,mlp.up_proj,0.0000411291,0.01000,2.034
217
+ 30,mlp.gate_proj,0.0000354981,0.01000,2.003
218
+ 30,mlp.down_proj,0.0000166990,0.01000,6.158
219
+ 31,self_attn.k_proj,0.0000048687,0.01000,1.867
220
+ 31,self_attn.v_proj,0.0000040193,0.01000,1.842
221
+ 31,self_attn.q_proj,0.0000189473,0.01000,1.897
222
+ 31,self_attn.o_proj,0.0000054662,0.01000,1.928
223
+ 31,mlp.up_proj,0.0000457638,0.01000,2.001
224
+ 31,mlp.gate_proj,0.0000403368,0.01000,2.053
225
+ 31,mlp.down_proj,0.0000203712,0.01000,6.115
226
+ 32,self_attn.k_proj,0.0000053250,0.01000,1.836
227
+ 32,self_attn.v_proj,0.0000053774,0.01000,1.829
228
+ 32,self_attn.q_proj,0.0000208265,0.01000,1.948
229
+ 32,self_attn.o_proj,0.0000054974,0.01000,1.923
230
+ 32,mlp.up_proj,0.0000489943,0.01000,2.010
231
+ 32,mlp.gate_proj,0.0000443471,0.01000,2.022
232
+ 32,mlp.down_proj,0.0000236334,0.01000,6.119
233
+ 33,self_attn.k_proj,0.0000055528,0.01000,1.860
234
+ 33,self_attn.v_proj,0.0000053279,0.01000,1.855
235
+ 33,self_attn.q_proj,0.0000225135,0.01000,1.882
236
+ 33,self_attn.o_proj,0.0000065416,0.01000,1.911
237
+ 33,mlp.up_proj,0.0000581524,0.01000,1.989
238
+ 33,mlp.gate_proj,0.0000532374,0.01000,1.992
239
+ 33,mlp.down_proj,0.0000341816,0.01000,6.194
240
+ 34,self_attn.k_proj,0.0000057969,0.01000,1.865
241
+ 34,self_attn.v_proj,0.0000065100,0.01000,1.820
242
+ 34,self_attn.q_proj,0.0000247060,0.01000,1.933
243
+ 34,self_attn.o_proj,0.0000064140,0.01000,1.974
244
+ 34,mlp.up_proj,0.0000676059,0.01000,1.996
245
+ 34,mlp.gate_proj,0.0000639034,0.01000,1.969
246
+ 34,mlp.down_proj,0.0000421207,0.01000,6.114
247
+ 35,self_attn.k_proj,0.0000056806,0.01000,1.843
248
+ 35,self_attn.v_proj,0.0000058037,0.01000,1.859
249
+ 35,self_attn.q_proj,0.0000227509,0.01000,1.864
250
+ 35,self_attn.o_proj,0.0000107215,0.01000,1.953
251
+ 35,mlp.up_proj,0.0000773738,0.01000,2.075
252
+ 35,mlp.gate_proj,0.0000748045,0.01000,2.003
253
+ 35,mlp.down_proj,0.0000531376,0.01000,6.151
254
+ 36,self_attn.k_proj,0.0000064778,0.01000,1.826
255
+ 36,self_attn.v_proj,0.0000105387,0.01000,1.820
256
+ 36,self_attn.q_proj,0.0000284083,0.01000,1.898
257
+ 36,self_attn.o_proj,0.0000097221,0.01000,1.959
258
+ 36,mlp.up_proj,0.0000858965,0.01000,2.012
259
+ 36,mlp.gate_proj,0.0000823549,0.01000,2.042
260
+ 36,mlp.down_proj,0.0000657707,0.01000,6.164
261
+ 37,self_attn.k_proj,0.0000074679,0.01000,1.836
262
+ 37,self_attn.v_proj,0.0000103437,0.01000,1.870
263
+ 37,self_attn.q_proj,0.0000301686,0.01000,1.843
264
+ 37,self_attn.o_proj,0.0000103363,0.01000,1.949
265
+ 37,mlp.up_proj,0.0000963696,0.01000,2.029
266
+ 37,mlp.gate_proj,0.0000927627,0.01000,1.995
267
+ 37,mlp.down_proj,0.0000759659,0.01000,6.172
268
+ 38,self_attn.k_proj,0.0000072543,0.01000,1.906
269
+ 38,self_attn.v_proj,0.0000103870,0.01000,1.833
270
+ 38,self_attn.q_proj,0.0000302236,0.01000,1.885
271
+ 38,self_attn.o_proj,0.0000106793,0.01000,1.909
272
+ 38,mlp.up_proj,0.0001080096,0.01000,1.994
273
+ 38,mlp.gate_proj,0.0001029393,0.01000,2.037
274
+ 38,mlp.down_proj,0.0000864311,0.01000,6.118
275
+ 39,self_attn.k_proj,0.0000070753,0.01000,1.848
276
+ 39,self_attn.v_proj,0.0000115101,0.01000,1.855
277
+ 39,self_attn.q_proj,0.0000317167,0.01000,1.926
278
+ 39,self_attn.o_proj,0.0000149693,0.01000,1.908
279
+ 39,mlp.up_proj,0.0001216658,0.01000,2.038
280
+ 39,mlp.gate_proj,0.0001149202,0.01000,2.005
281
+ 39,mlp.down_proj,0.0001039416,0.01000,6.191
282
+ 40,self_attn.k_proj,0.0000081462,0.01000,1.824
283
+ 40,self_attn.v_proj,0.0000157852,0.01000,1.910
284
+ 40,self_attn.q_proj,0.0000353841,0.01000,1.991
285
+ 40,self_attn.o_proj,0.0000151671,0.01000,1.913
286
+ 40,mlp.up_proj,0.0001326770,0.01000,2.002
287
+ 40,mlp.gate_proj,0.0001247391,0.01000,2.012
288
+ 40,mlp.down_proj,0.0001193831,0.01000,6.104
289
+ 41,self_attn.k_proj,0.0000079063,0.01000,1.881
290
+ 41,self_attn.v_proj,0.0000165749,0.01000,1.930
291
+ 41,self_attn.q_proj,0.0000366510,0.01000,1.896
292
+ 41,self_attn.o_proj,0.0000124038,0.01000,1.877
293
+ 41,mlp.up_proj,0.0001447803,0.01000,1.999
294
+ 41,mlp.gate_proj,0.0001340893,0.01000,1.963
295
+ 41,mlp.down_proj,0.0001349494,0.01000,6.061
296
+ 42,self_attn.k_proj,0.0000083146,0.01000,1.833
297
+ 42,self_attn.v_proj,0.0000181338,0.01000,1.793
298
+ 42,self_attn.q_proj,0.0000357798,0.01000,1.855
299
+ 42,self_attn.o_proj,0.0000141514,0.01000,1.914
300
+ 42,mlp.up_proj,0.0001559160,0.01000,1.990
301
+ 42,mlp.gate_proj,0.0001425551,0.01000,1.997
302
+ 42,mlp.down_proj,0.0001580665,0.01000,6.099
303
+ 43,self_attn.k_proj,0.0000083956,0.01000,1.822
304
+ 43,self_attn.v_proj,0.0000256210,0.01000,1.813
305
+ 43,self_attn.q_proj,0.0000399949,0.01000,1.861
306
+ 43,self_attn.o_proj,0.0000247247,0.01000,1.883
307
+ 43,mlp.up_proj,0.0001706939,0.01000,2.020
308
+ 43,mlp.gate_proj,0.0001531956,0.01000,2.037
309
+ 43,mlp.down_proj,0.0001867778,0.01000,6.179
310
+ 44,self_attn.k_proj,0.0000076330,0.01000,1.852
311
+ 44,self_attn.v_proj,0.0000281914,0.01000,1.820
312
+ 44,self_attn.q_proj,0.0000391793,0.01000,1.889
313
+ 44,self_attn.o_proj,0.0000360502,0.01000,1.884
314
+ 44,mlp.up_proj,0.0001831046,0.01000,1.963
315
+ 44,mlp.gate_proj,0.0001616602,0.01000,1.966
316
+ 44,mlp.down_proj,0.0002535868,0.01000,6.108
317
+ 45,self_attn.k_proj,0.0000079784,0.01000,1.892
318
+ 45,self_attn.v_proj,0.0000340295,0.01000,1.838
319
+ 45,self_attn.q_proj,0.0000422606,0.01000,1.895
320
+ 45,self_attn.o_proj,0.0000337677,0.01000,1.944
321
+ 45,mlp.up_proj,0.0001918452,0.01000,1.990
322
+ 45,mlp.gate_proj,0.0001717587,0.01000,1.985
323
+ 45,mlp.down_proj,0.0002833572,0.01000,6.189
324
+ 46,self_attn.k_proj,0.0000071048,0.01000,1.838
325
+ 46,self_attn.v_proj,0.0000363993,0.01000,1.838
326
+ 46,self_attn.q_proj,0.0000375253,0.01000,1.876
327
+ 46,self_attn.o_proj,0.0000640068,0.01000,1.919
328
+ 46,mlp.up_proj,0.0001911036,0.01000,2.009
329
+ 46,mlp.gate_proj,0.0001784168,0.01000,2.081
330
+ 46,mlp.down_proj,0.0004206370,0.01000,6.225
331
+ 47,self_attn.k_proj,0.0000061165,0.01000,1.837
332
+ 47,self_attn.v_proj,0.0000228788,0.01000,1.920
333
+ 47,self_attn.q_proj,0.0000279219,0.01000,1.940
334
+ 47,self_attn.o_proj,0.0000288922,0.01000,1.906
335
+ 47,mlp.up_proj,0.0002043838,0.01000,2.035
336
+ 47,mlp.gate_proj,0.0001966780,0.01000,2.033
337
+ 47,mlp.down_proj,0.0006320129,0.01000,6.199
quantize_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:3.0.0-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
+ "v2": false,
21
+ "v2_alpha": 0.25
22
+ }
23
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|fim_pad|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|end▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|User|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<|Assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<|begin▁of▁sentence|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin��>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
185
+ "clean_up_tokenization_spaces": false,
186
+ "eos_token": "<|end▁of▁sentence|>",
187
+ "extra_special_tokens": {},
188
+ "legacy": true,
189
+ "model_max_length": 16384,
190
+ "pad_token": "<|fim_pad|>",
191
+ "sp_model_kwargs": {},
192
+ "tokenizer_class": "LlamaTokenizerFast",
193
+ "unk_token": null,
194
+ "use_default_system_prompt": false
195
+ }