Hugging Face's logo

normalcomputing
/
extended-mind-mpt-7b

Text Generation
Transformers
PyTorch
extended-mpt
custom_code
Model card Files Community
4
phoebeklett commited on
Commit
0effbcc
•
1 Parent(s): ffccc9a

Upload ExtendedMPTForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +93 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +201 -0
config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mosaicml/mpt-7b",
3
+ "architectures": [
4
+ "ExtendedMPTForCausalLM"
5
+ ],
6
+ "attn_config": {
7
+ "alibi": true,
8
+ "alibi_bias_max": 8,
9
+ "attn_impl": "torch",
10
+ "attn_pdrop": 0,
11
+ "attn_type": "multihead_attention",
12
+ "attn_uses_sequence_id": false,
13
+ "clip_qkv": null,
14
+ "mask_by_sim": true,
15
+ "memory_type": "manual",
16
+ "prefix_lm": false,
17
+ "qk_ln": false,
18
+ "sim_threshold": 0.25,
19
+ "softmax_scale": null,
20
+ "topk": 10,
21
+ "use_active_externalism": true
22
+ },
23
+ "auto_map": {
24
+ "AutoConfig": "mosaicml/mpt-7b--configuration_mpt.MPTConfig",
25
+ "AutoModelForCausalLM": "mosaicml/mpt-7b--modeling_mpt.MPTForCausalLM"
26
+ },
27
+ "d_model": 4096,
28
+ "emb_pdrop": 0,
29
+ "embedding_fraction": 1.0,
30
+ "expansion_ratio": 4,
31
+ "init_config": {
32
+ "emb_init_std": null,
33
+ "emb_init_uniform_lim": null,
34
+ "fan_mode": "fan_in",
35
+ "init_div_is_residual": true,
36
+ "init_gain": 0,
37
+ "init_nonlinearity": "relu",
38
+ "init_std": 0.02,
39
+ "name": "kaiming_normal_",
40
+ "verbose": 0
41
+ },
42
+ "init_device": "cpu",
43
+ "learned_pos_emb": true,
44
+ "logit_scale": null,
45
+ "max_seq_len": 2048,
46
+ "memory_device": "cpu",
47
+ "model_type": "extended-mpt",
48
+ "n_heads": 32,
49
+ "n_layers": 32,
50
+ "no_bias": true,
51
+ "norm_type": "low_precision_layernorm",
52
+ "resid_pdrop": 0,
53
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.30.0",
56
+ "use_active_externalism_by_layer": [
57
+ true,
58
+ true,
59
+ true,
60
+ true,
61
+ true,
62
+ true,
63
+ true,
64
+ true,
65
+ true,
66
+ true,
67
+ true,
68
+ true,
69
+ true,
70
+ true,
71
+ true,
72
+ true,
73
+ true,
74
+ true,
75
+ true,
76
+ true,
77
+ true,
78
+ true,
79
+ true,
80
+ true,
81
+ true,
82
+ true,
83
+ true,
84
+ true,
85
+ true,
86
+ true,
87
+ true,
88
+ true
89
+ ],
90
+ "use_cache": false,
91
+ "verbose": 0,
92
+ "vocab_size": 50432
93
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "transformers_version": "4.30.0",
5
+ "use_cache": false
6
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea820d083ffcff5956a24d97c33088ff4d5cbf679539289b02874ea0c254f61e
3
+ size 9953500837
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb29477b4a14843ead9e1102425e9e0ab4547fc3eaa26ca40080c735121eb02a
3
+ size 9932530109
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1655594702d808ad28baf0154da71d098702c6cb1f660c0d4f059abb32a00e11
3
+ size 6711181899
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26597146624
4
+ },
5
+ "weight_map": {
6
+ "transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
7
+ "transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
8
+ "transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
9
+ "transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
27
+ "transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
28
+ "transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
31
+ "transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
32
+ "transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
33
+ "transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
34
+ "transformer.blocks.12.norm_1.weight": "pytorch_model-00002-of-00003.bin",
35
+ "transformer.blocks.12.norm_2.weight": "pytorch_model-00002-of-00003.bin",
36
+ "transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
37
+ "transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
38
+ "transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
39
+ "transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
40
+ "transformer.blocks.13.norm_1.weight": "pytorch_model-00002-of-00003.bin",
41
+ "transformer.blocks.13.norm_2.weight": "pytorch_model-00002-of-00003.bin",
42
+ "transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
43
+ "transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
44
+ "transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
45
+ "transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
46
+ "transformer.blocks.14.norm_1.weight": "pytorch_model-00002-of-00003.bin",
47
+ "transformer.blocks.14.norm_2.weight": "pytorch_model-00002-of-00003.bin",
48
+ "transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
49
+ "transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "transformer.blocks.15.norm_1.weight": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.blocks.15.norm_2.weight": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.blocks.16.norm_1.weight": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.blocks.16.norm_2.weight": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.blocks.17.norm_1.weight": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.blocks.17.norm_2.weight": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.blocks.18.norm_1.weight": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.blocks.18.norm_2.weight": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.blocks.19.norm_1.weight": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.blocks.19.norm_2.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
79
+ "transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
80
+ "transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
81
+ "transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
82
+ "transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00003.bin",
83
+ "transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00003.bin",
84
+ "transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.blocks.20.norm_1.weight": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.blocks.20.norm_2.weight": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.blocks.21.norm_1.weight": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.blocks.21.norm_2.weight": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.blocks.22.norm_1.weight": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.blocks.22.norm_2.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
105
+ "transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "transformer.blocks.23.norm_1.weight": "pytorch_model-00002-of-00003.bin",
107
+ "transformer.blocks.23.norm_2.weight": "pytorch_model-00002-of-00003.bin",
108
+ "transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
109
+ "transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
110
+ "transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
111
+ "transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
112
+ "transformer.blocks.24.norm_1.weight": "pytorch_model-00003-of-00003.bin",
113
+ "transformer.blocks.24.norm_2.weight": "pytorch_model-00003-of-00003.bin",
114
+ "transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
115
+ "transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
116
+ "transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
117
+ "transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
118
+ "transformer.blocks.25.norm_1.weight": "pytorch_model-00003-of-00003.bin",
119
+ "transformer.blocks.25.norm_2.weight": "pytorch_model-00003-of-00003.bin",
120
+ "transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
121
+ "transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
122
+ "transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
123
+ "transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
124
+ "transformer.blocks.26.norm_1.weight": "pytorch_model-00003-of-00003.bin",
125
+ "transformer.blocks.26.norm_2.weight": "pytorch_model-00003-of-00003.bin",
126
+ "transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
127
+ "transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
128
+ "transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
129
+ "transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
130
+ "transformer.blocks.27.norm_1.weight": "pytorch_model-00003-of-00003.bin",
131
+ "transformer.blocks.27.norm_2.weight": "pytorch_model-00003-of-00003.bin",
132
+ "transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
133
+ "transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
134
+ "transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
135
+ "transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
136
+ "transformer.blocks.28.norm_1.weight": "pytorch_model-00003-of-00003.bin",
137
+ "transformer.blocks.28.norm_2.weight": "pytorch_model-00003-of-00003.bin",
138
+ "transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
139
+ "transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
140
+ "transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
141
+ "transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
142
+ "transformer.blocks.29.norm_1.weight": "pytorch_model-00003-of-00003.bin",
143
+ "transformer.blocks.29.norm_2.weight": "pytorch_model-00003-of-00003.bin",
144
+ "transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
145
+ "transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
146
+ "transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
147
+ "transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
148
+ "transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00003.bin",
149
+ "transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00003.bin",
150
+ "transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
151
+ "transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
152
+ "transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
153
+ "transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
154
+ "transformer.blocks.30.norm_1.weight": "pytorch_model-00003-of-00003.bin",
155
+ "transformer.blocks.30.norm_2.weight": "pytorch_model-00003-of-00003.bin",
156
+ "transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
157
+ "transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
158
+ "transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
159
+ "transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
160
+ "transformer.blocks.31.norm_1.weight": "pytorch_model-00003-of-00003.bin",
161
+ "transformer.blocks.31.norm_2.weight": "pytorch_model-00003-of-00003.bin",
162
+ "transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
163
+ "transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
164
+ "transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
165
+ "transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
166
+ "transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00003.bin",
167
+ "transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00003.bin",
168
+ "transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
169
+ "transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
170
+ "transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
171
+ "transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
172
+ "transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00003.bin",
173
+ "transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00003.bin",
174
+ "transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
175
+ "transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
176
+ "transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
177
+ "transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
178
+ "transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00003.bin",
179
+ "transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00003.bin",
180
+ "transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
181
+ "transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
182
+ "transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
183
+ "transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
184
+ "transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00003.bin",
185
+ "transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00003.bin",
186
+ "transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
187
+ "transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
188
+ "transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
189
+ "transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
190
+ "transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00003.bin",
191
+ "transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00003.bin",
192
+ "transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
193
+ "transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
194
+ "transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
195
+ "transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
196
+ "transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00003.bin",
197
+ "transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00003.bin",
198
+ "transformer.norm_f.weight": "pytorch_model-00003-of-00003.bin",
199
+ "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
200
+ }
201
+ }