sumangpt commited on
Commit
c25e7e1
1 Parent(s): 9132277

Upload FalconForCausalLM

Browse files
config.json CHANGED
@@ -28,19 +28,7 @@
28
  "num_hidden_layers": 32,
29
  "num_kv_heads": 71,
30
  "parallel_attn": true,
31
- "quantization_config": {
32
- "bnb_4bit_compute_dtype": "bfloat16",
33
- "bnb_4bit_quant_type": "nf4",
34
- "bnb_4bit_use_double_quant": true,
35
- "llm_int8_enable_fp32_cpu_offload": false,
36
- "llm_int8_has_fp16_weight": false,
37
- "llm_int8_skip_modules": null,
38
- "llm_int8_threshold": 6.0,
39
- "load_in_4bit": true,
40
- "load_in_8bit": false,
41
- "quant_method": "bitsandbytes"
42
- },
43
- "torch_dtype": "float16",
44
  "transformers_version": "4.37.0.dev0",
45
  "use_cache": true,
46
  "vocab_size": 65024
 
28
  "num_hidden_layers": 32,
29
  "num_kv_heads": 71,
30
  "parallel_attn": true,
31
+ "torch_dtype": "float32",
 
 
 
 
 
 
 
 
 
 
 
 
32
  "transformers_version": "4.37.0.dev0",
33
  "use_cache": true,
34
  "vocab_size": 65024
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974824e9a5e19cd6a5cadc1fd79e5c12245e0bc7993125f374eed9fe8550975b
3
+ size 4992877824
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d86e052620f1151b9e2ae2038f159c80c931dc56990fc5857d7bc7f61d4cd4
3
+ size 4969686200
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4198ca16a4022f80c56474bb0b004ff8cf76c9ff75893d6ac41fb02a9e6355f3
3
+ size 4969686224
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c6ce1fc61d4c38489c22c26413c05c09687aff519a6cb749d6c5f1b9460e97
3
+ size 4969686224
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac412a5547d7583e54f6bd5d69d0d3e6c8156ce711c3cf5e26f54b947893c94c
3
+ size 4969686224
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9320b00a0e71511e334bdada726dae53f294bde6d1814cb3ca1e40ba0173913e
3
+ size 2815283328
model.safetensors.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27686882816
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
9
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
10
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00006.safetensors",
11
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
12
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
13
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
14
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
15
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
16
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
17
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
18
+ "transformer.h.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
19
+ "transformer.h.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
20
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
21
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
22
+ "transformer.h.10.self_attention.dense.weight": "model-00002-of-00006.safetensors",
23
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
24
+ "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
25
+ "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
26
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
27
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
28
+ "transformer.h.11.self_attention.dense.weight": "model-00003-of-00006.safetensors",
29
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
30
+ "transformer.h.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
31
+ "transformer.h.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
32
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
33
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
34
+ "transformer.h.12.self_attention.dense.weight": "model-00003-of-00006.safetensors",
35
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
36
+ "transformer.h.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
37
+ "transformer.h.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
38
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
39
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
40
+ "transformer.h.13.self_attention.dense.weight": "model-00003-of-00006.safetensors",
41
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
42
+ "transformer.h.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
43
+ "transformer.h.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
44
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
45
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
46
+ "transformer.h.14.self_attention.dense.weight": "model-00003-of-00006.safetensors",
47
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
48
+ "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
49
+ "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
50
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
51
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
52
+ "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
53
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
54
+ "transformer.h.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
55
+ "transformer.h.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
56
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
57
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
58
+ "transformer.h.16.self_attention.dense.weight": "model-00003-of-00006.safetensors",
59
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
60
+ "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
61
+ "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
62
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
63
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
64
+ "transformer.h.17.self_attention.dense.weight": "model-00004-of-00006.safetensors",
65
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
66
+ "transformer.h.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
67
+ "transformer.h.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
68
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
69
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
70
+ "transformer.h.18.self_attention.dense.weight": "model-00004-of-00006.safetensors",
71
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
72
+ "transformer.h.19.input_layernorm.bias": "model-00004-of-00006.safetensors",
73
+ "transformer.h.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
74
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
75
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
76
+ "transformer.h.19.self_attention.dense.weight": "model-00004-of-00006.safetensors",
77
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
78
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
79
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
80
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
81
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
82
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00006.safetensors",
83
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
84
+ "transformer.h.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
85
+ "transformer.h.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
86
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
87
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
88
+ "transformer.h.20.self_attention.dense.weight": "model-00004-of-00006.safetensors",
89
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
90
+ "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
91
+ "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
92
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
93
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
94
+ "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
95
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
96
+ "transformer.h.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
97
+ "transformer.h.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
98
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
99
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
100
+ "transformer.h.22.self_attention.dense.weight": "model-00004-of-00006.safetensors",
101
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
102
+ "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
103
+ "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
104
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
105
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
106
+ "transformer.h.23.self_attention.dense.weight": "model-00005-of-00006.safetensors",
107
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
108
+ "transformer.h.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
109
+ "transformer.h.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
110
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
111
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
112
+ "transformer.h.24.self_attention.dense.weight": "model-00005-of-00006.safetensors",
113
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
114
+ "transformer.h.25.input_layernorm.bias": "model-00005-of-00006.safetensors",
115
+ "transformer.h.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
116
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
117
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
118
+ "transformer.h.25.self_attention.dense.weight": "model-00005-of-00006.safetensors",
119
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
120
+ "transformer.h.26.input_layernorm.bias": "model-00005-of-00006.safetensors",
121
+ "transformer.h.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
122
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
123
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
124
+ "transformer.h.26.self_attention.dense.weight": "model-00005-of-00006.safetensors",
125
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
126
+ "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
127
+ "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
128
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
129
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
130
+ "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
131
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
132
+ "transformer.h.28.input_layernorm.bias": "model-00006-of-00006.safetensors",
133
+ "transformer.h.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
134
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
135
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
136
+ "transformer.h.28.self_attention.dense.weight": "model-00005-of-00006.safetensors",
137
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
138
+ "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
139
+ "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
140
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
141
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
142
+ "transformer.h.29.self_attention.dense.weight": "model-00006-of-00006.safetensors",
143
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
144
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
145
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
146
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
147
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
148
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
149
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
150
+ "transformer.h.30.input_layernorm.bias": "model-00006-of-00006.safetensors",
151
+ "transformer.h.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
152
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
153
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
154
+ "transformer.h.30.self_attention.dense.weight": "model-00006-of-00006.safetensors",
155
+ "transformer.h.30.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
156
+ "transformer.h.31.input_layernorm.bias": "model-00006-of-00006.safetensors",
157
+ "transformer.h.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
158
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
159
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
160
+ "transformer.h.31.self_attention.dense.weight": "model-00006-of-00006.safetensors",
161
+ "transformer.h.31.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
162
+ "transformer.h.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
163
+ "transformer.h.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
164
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
165
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
166
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00006.safetensors",
167
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
168
+ "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
169
+ "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
170
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
171
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
172
+ "transformer.h.5.self_attention.dense.weight": "model-00002-of-00006.safetensors",
173
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
174
+ "transformer.h.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
175
+ "transformer.h.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
176
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
177
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
178
+ "transformer.h.6.self_attention.dense.weight": "model-00002-of-00006.safetensors",
179
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
180
+ "transformer.h.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
181
+ "transformer.h.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
182
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
183
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
184
+ "transformer.h.7.self_attention.dense.weight": "model-00002-of-00006.safetensors",
185
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
186
+ "transformer.h.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
187
+ "transformer.h.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
188
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
189
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
190
+ "transformer.h.8.self_attention.dense.weight": "model-00002-of-00006.safetensors",
191
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
192
+ "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
193
+ "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
194
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
195
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
196
+ "transformer.h.9.self_attention.dense.weight": "model-00002-of-00006.safetensors",
197
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
198
+ "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
199
+ "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
200
+ "transformer.word_embeddings.weight": "model-00001-of-00006.safetensors"
201
+ }
202
+ }