Hugging Face's logo

latimar
/
Phind-Codellama-34B-v2-megacode-exl2

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files Community
1
latimar commited on
Commit
9002778
•
1 Parent(s): 07fdefc

Add 3.0 quant weights

Browse files
Files changed (5) hide show
  1. 3.0/.gitattributes +43 -0
  2. 3.0/model.safetensors.index.json +442 -0
  3. 3.0/output-00001-of-00002.safetensors +3 -0
  4. 3.0/output-00002-of-00002.safetensors +3 -0
  5. README.md +26 -15
3.0/.gitattributes ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ pytorch_model-00006-of-00007.bin filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model-00007-of-00007.bin filter=lfs diff=lfs merge=lfs -text
38
+ pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
39
+ pytorch_model-00001-of-00007.bin filter=lfs diff=lfs merge=lfs -text
40
+ pytorch_model-00002-of-00007.bin filter=lfs diff=lfs merge=lfs -text
41
+ pytorch_model-00003-of-00007.bin filter=lfs diff=lfs merge=lfs -text
42
+ pytorch_model-00004-of-00007.bin filter=lfs diff=lfs merge=lfs -text
43
+ pytorch_model-00005-of-00007.bin filter=lfs diff=lfs merge=lfs -text
3.0/model.safetensors.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 67487940608
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00007-of-00007.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00007-of-00007.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00007-of-00007.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00007-of-00007.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00007-of-00007.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00007-of-00007.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
395
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
396
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
397
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
398
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
399
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
400
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
405
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
406
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
407
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
408
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
409
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
410
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
411
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
412
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
413
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
414
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
415
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
416
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
417
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
419
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
420
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
421
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
422
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
423
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
424
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
425
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
426
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
427
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
428
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
429
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
430
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
431
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
432
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
433
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
434
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
435
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
436
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
437
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
438
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
440
+ "model.norm.weight": "model-00007-of-00007.safetensors"
441
+ }
442
+ }
3.0/output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8ceb8dd847d47597597d1716369fe762261ea89b5ea97f1126d0890ab1f032
3
+ size 8531876384
3.0/output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac0eb9554c65ae8ec7b06940fac8b5d7f0238dbcfa06574765761c132d427cb
3
+ size 4730652840
README.md CHANGED
@@ -16,21 +16,12 @@ to [EXL2](https://github.com/turboderp/exllamav2#exl2-quantization) format.
16
  Converted with the ExllamaV2 [convert.py](https://github.com/turboderp/exllamav2/blob/master/convert.py) script,
17
  exllamav2 [commit](https://github.com/turboderp/exllamav2/commit/31f31e1b08eeccf4a5ab31fd202ef3100dce8d22)
18
 
19
-
20
- | BPW (hb=8) | Human-Eval | Evol-Ins PPL | Wiki PPL | File Size (Gb) |
21
- | ----------- | ----------- | ------------ | ---------- | -------------- |
22
- | 2.55 | 0.402439 | 2.0944 | 18.9843 | 10.62 |
23
- | 2.8 | 0.634146 | 2.0814 | 17.6326 | 11.58 |
24
- | 3.0 | 0.664634 | 2.0600 | 11.2096 | 12.36 |
25
- | 4.625 | 0.701219 | 2.0401 | 6.7243 | 18.63 |
26
-
27
  ## Datasets used for calibration and PPL measurement
28
 
29
  * [Calibration](https://huggingface.co/datasets/rombodawg/2XUNCENSORED_MegaCodeTraining188k)
30
  * [Wiki](https://huggingface.co/datasets/wikitext/blob/refs%2Fconvert%2Fparquet/wikitext-2-v1/validation/0000.parquet)
31
  * [Evol-Ins](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/blob/refs%2Fconvert%2Fparquet/default/train/0000.parquet)
32
 
33
-
34
  ### Conversion
35
 
36
  Conversion arguments:
@@ -50,7 +41,7 @@ test_inference.py -m ${MODEL_DIR_EXL} -ed ${PPL_DATASET}
50
 
51
  ### Human-Eval
52
 
53
- For the point of reference, Phind says that the original model achieves **73.8** Human-Eval score.
54
 
55
  Samples for the Human-Eval scores of EXL2 quants were generated with [exl2.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/exl2.human-eval.py)
56
  script:
@@ -58,13 +49,33 @@ script:
58
  python exl2.human-eval.py -m ${MODEL_DIR_EXL2} -c 4096 -o ${BPW}-samples.jsonl
59
  ```
60
 
61
- Unfortunately, FP16/INT8 weights of this model won't fit on my RTX 4090, but FP16 quantized to NF4 fits,
62
- so I generated samples with [tf.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/tf.human-eval.py) script:
63
  ```
64
  python tf.human-eval.py -m ${MODEL_DIR_FP16} -o nf4-samples.jsonl
65
  ```
66
 
67
- NF4 variant gives us **0.70731707**
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
- As another reference, [EXL2 3.2-bpw quant](https://huggingface.co/firelzrd/Phind-CodeLlama-34B-v2-exl2/tree/3_2-bpw) of this model by [firelzrd](https://huggingface.co/firelzrd)
70
- yields **0.609756** Human-Eval score.
 
16
  Converted with the ExllamaV2 [convert.py](https://github.com/turboderp/exllamav2/blob/master/convert.py) script,
17
  exllamav2 [commit](https://github.com/turboderp/exllamav2/commit/31f31e1b08eeccf4a5ab31fd202ef3100dce8d22)
18
 
 
 
 
 
 
 
 
 
19
  ## Datasets used for calibration and PPL measurement
20
 
21
  * [Calibration](https://huggingface.co/datasets/rombodawg/2XUNCENSORED_MegaCodeTraining188k)
22
  * [Wiki](https://huggingface.co/datasets/wikitext/blob/refs%2Fconvert%2Fparquet/wikitext-2-v1/validation/0000.parquet)
23
  * [Evol-Ins](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/blob/refs%2Fconvert%2Fparquet/default/train/0000.parquet)
24
 
 
25
  ### Conversion
26
 
27
  Conversion arguments:
 
41
 
42
  ### Human-Eval
43
 
44
+ #### Evaluation
45
 
46
  Samples for the Human-Eval scores of EXL2 quants were generated with [exl2.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/exl2.human-eval.py)
47
  script:
 
49
  python exl2.human-eval.py -m ${MODEL_DIR_EXL2} -c 4096 -o ${BPW}-samples.jsonl
50
  ```
51
 
52
+ Human-Eval samples of NF4/INT8 quants were generated with [tf.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/tf.human-eval.py) script:
 
53
  ```
54
  python tf.human-eval.py -m ${MODEL_DIR_FP16} -o nf4-samples.jsonl
55
  ```
56
 
57
+ #### Comparison
58
+
59
+ Phind says that the original model in full weights achieves **73.8** Human-Eval score.
60
+ NF4 quant gives me **70.73**
61
+
62
+ WizardCoder models claimed Human-Eval scores (full weights):
63
+
64
+ | Model | Score |
65
+ | ----- | ----- |
66
+ | WizardCoder-Python-34B-V1.0 | 73.2 |
67
+ | WizardCoder-Python-13B-V1.0 | 64.0 |
68
+
69
+ Vanilla Mistral-7B INT8 scores **27.43**
70
+
71
+ [EXL2 3.2-bpw quant](https://huggingface.co/firelzrd/Phind-CodeLlama-34B-v2-exl2/tree/3_2-bpw) of this model by [firelzrd](https://huggingface.co/firelzrd)
72
+ scores **60.97**.
73
+
74
+
75
+ | BPW (hb=8) | HumanEval | Evol-Ins PPL | Wiki PPL | File Size (Gb) |
76
+ | ----------- | --------- | ------------ | ---------- | -------------- |
77
+ | 2.55 | **40.24** | 2.0944 | 18.9843 | 10.62 |
78
+ | 2.8 | **63.41** | 2.0814 | 17.6326 | 11.58 |
79
+ | 3.0 | **66.46** | 2.0600 | 11.2096 | 12.36 |
80
+ | 4.625 | **70.12** | 2.0401 | 6.7243 | 18.63 |
81