fmilletari-czi commited on
Commit
dc1bbe1
·
verified ·
1 Parent(s): e35650a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ESMCForMaskedLM"
4
+ ],
5
+ "classifier_dropout": 0.1,
6
+ "d_model": 2560,
7
+ "dtype": "float32",
8
+ "initializer_range": 0.02,
9
+ "mask_token_id": 31,
10
+ "model_type": "esmc",
11
+ "n_heads": 40,
12
+ "n_layers": 80,
13
+ "pad_token_id": 1,
14
+ "tie_word_embeddings": false,
15
+ "transformers_version": "4.57.6",
16
+ "vocab_size": 64
17
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b5a29ad5e2845e2cd76a9d0797a5e2606daa69813da4829230f65871e51635
3
+ size 4864457920
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7e67e4ec74123cbfbf46925a047e8450beac7cf4fafc6a630bb88af41f773b
3
+ size 4971211344
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3c29afea073517b2cbc3ad21730f78f6dbd83ba154ea5c29146c6f6ffaf27c
3
+ size 4863752992
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edeab18071caa3933ccf8c20ee4d07acb53f87f4280f27095ebe97a6af1649e
3
+ size 4971211344
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a243e24b1efba662a6f3a95961ef3d24fcfa9ed06a3dbb46e8e72f885f64620
3
+ size 4863752992
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d2c00b9b021dd8d03ccd680b6dabd1efc0350ecac0c9489627691f5d83941f
3
+ size 873762296
model.safetensors.index.json ADDED
@@ -0,0 +1,1056 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 6352005184,
4
+ "total_size": 25408020736
5
+ },
6
+ "weight_map": {
7
+ "esmc.embed.weight": "model-00001-of-00006.safetensors",
8
+ "esmc.transformer.blocks.0.attn.k_ln.weight": "model-00001-of-00006.safetensors",
9
+ "esmc.transformer.blocks.0.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
10
+ "esmc.transformer.blocks.0.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
11
+ "esmc.transformer.blocks.0.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
12
+ "esmc.transformer.blocks.0.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
13
+ "esmc.transformer.blocks.0.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
14
+ "esmc.transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00006.safetensors",
15
+ "esmc.transformer.blocks.0.attn.q_ln.weight": "model-00001-of-00006.safetensors",
16
+ "esmc.transformer.blocks.0.ffn._extra_state": "model-00001-of-00006.safetensors",
17
+ "esmc.transformer.blocks.0.ffn.fc1_weight": "model-00001-of-00006.safetensors",
18
+ "esmc.transformer.blocks.0.ffn.fc2_weight": "model-00001-of-00006.safetensors",
19
+ "esmc.transformer.blocks.0.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
20
+ "esmc.transformer.blocks.0.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
21
+ "esmc.transformer.blocks.1.attn.k_ln.weight": "model-00001-of-00006.safetensors",
22
+ "esmc.transformer.blocks.1.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
23
+ "esmc.transformer.blocks.1.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
24
+ "esmc.transformer.blocks.1.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
25
+ "esmc.transformer.blocks.1.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
26
+ "esmc.transformer.blocks.1.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
27
+ "esmc.transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00006.safetensors",
28
+ "esmc.transformer.blocks.1.attn.q_ln.weight": "model-00001-of-00006.safetensors",
29
+ "esmc.transformer.blocks.1.ffn._extra_state": "model-00001-of-00006.safetensors",
30
+ "esmc.transformer.blocks.1.ffn.fc1_weight": "model-00001-of-00006.safetensors",
31
+ "esmc.transformer.blocks.1.ffn.fc2_weight": "model-00001-of-00006.safetensors",
32
+ "esmc.transformer.blocks.1.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
33
+ "esmc.transformer.blocks.1.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
34
+ "esmc.transformer.blocks.10.attn.k_ln.weight": "model-00001-of-00006.safetensors",
35
+ "esmc.transformer.blocks.10.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
36
+ "esmc.transformer.blocks.10.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
37
+ "esmc.transformer.blocks.10.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
38
+ "esmc.transformer.blocks.10.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
39
+ "esmc.transformer.blocks.10.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
40
+ "esmc.transformer.blocks.10.attn.out_proj.weight": "model-00001-of-00006.safetensors",
41
+ "esmc.transformer.blocks.10.attn.q_ln.weight": "model-00001-of-00006.safetensors",
42
+ "esmc.transformer.blocks.10.ffn._extra_state": "model-00001-of-00006.safetensors",
43
+ "esmc.transformer.blocks.10.ffn.fc1_weight": "model-00001-of-00006.safetensors",
44
+ "esmc.transformer.blocks.10.ffn.fc2_weight": "model-00001-of-00006.safetensors",
45
+ "esmc.transformer.blocks.10.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
46
+ "esmc.transformer.blocks.10.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
47
+ "esmc.transformer.blocks.11.attn.k_ln.weight": "model-00001-of-00006.safetensors",
48
+ "esmc.transformer.blocks.11.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
49
+ "esmc.transformer.blocks.11.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
50
+ "esmc.transformer.blocks.11.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
51
+ "esmc.transformer.blocks.11.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
52
+ "esmc.transformer.blocks.11.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
53
+ "esmc.transformer.blocks.11.attn.out_proj.weight": "model-00001-of-00006.safetensors",
54
+ "esmc.transformer.blocks.11.attn.q_ln.weight": "model-00001-of-00006.safetensors",
55
+ "esmc.transformer.blocks.11.ffn._extra_state": "model-00001-of-00006.safetensors",
56
+ "esmc.transformer.blocks.11.ffn.fc1_weight": "model-00001-of-00006.safetensors",
57
+ "esmc.transformer.blocks.11.ffn.fc2_weight": "model-00001-of-00006.safetensors",
58
+ "esmc.transformer.blocks.11.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
59
+ "esmc.transformer.blocks.11.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
60
+ "esmc.transformer.blocks.12.attn.k_ln.weight": "model-00001-of-00006.safetensors",
61
+ "esmc.transformer.blocks.12.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
62
+ "esmc.transformer.blocks.12.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
63
+ "esmc.transformer.blocks.12.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
64
+ "esmc.transformer.blocks.12.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
65
+ "esmc.transformer.blocks.12.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
66
+ "esmc.transformer.blocks.12.attn.out_proj.weight": "model-00001-of-00006.safetensors",
67
+ "esmc.transformer.blocks.12.attn.q_ln.weight": "model-00001-of-00006.safetensors",
68
+ "esmc.transformer.blocks.12.ffn._extra_state": "model-00001-of-00006.safetensors",
69
+ "esmc.transformer.blocks.12.ffn.fc1_weight": "model-00001-of-00006.safetensors",
70
+ "esmc.transformer.blocks.12.ffn.fc2_weight": "model-00001-of-00006.safetensors",
71
+ "esmc.transformer.blocks.12.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
72
+ "esmc.transformer.blocks.12.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
73
+ "esmc.transformer.blocks.13.attn.k_ln.weight": "model-00001-of-00006.safetensors",
74
+ "esmc.transformer.blocks.13.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
75
+ "esmc.transformer.blocks.13.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
76
+ "esmc.transformer.blocks.13.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
77
+ "esmc.transformer.blocks.13.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
78
+ "esmc.transformer.blocks.13.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
79
+ "esmc.transformer.blocks.13.attn.out_proj.weight": "model-00001-of-00006.safetensors",
80
+ "esmc.transformer.blocks.13.attn.q_ln.weight": "model-00001-of-00006.safetensors",
81
+ "esmc.transformer.blocks.13.ffn._extra_state": "model-00001-of-00006.safetensors",
82
+ "esmc.transformer.blocks.13.ffn.fc1_weight": "model-00001-of-00006.safetensors",
83
+ "esmc.transformer.blocks.13.ffn.fc2_weight": "model-00001-of-00006.safetensors",
84
+ "esmc.transformer.blocks.13.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
85
+ "esmc.transformer.blocks.13.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
86
+ "esmc.transformer.blocks.14.attn.k_ln.weight": "model-00001-of-00006.safetensors",
87
+ "esmc.transformer.blocks.14.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
88
+ "esmc.transformer.blocks.14.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
89
+ "esmc.transformer.blocks.14.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
90
+ "esmc.transformer.blocks.14.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
91
+ "esmc.transformer.blocks.14.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
92
+ "esmc.transformer.blocks.14.attn.out_proj.weight": "model-00001-of-00006.safetensors",
93
+ "esmc.transformer.blocks.14.attn.q_ln.weight": "model-00001-of-00006.safetensors",
94
+ "esmc.transformer.blocks.14.ffn._extra_state": "model-00001-of-00006.safetensors",
95
+ "esmc.transformer.blocks.14.ffn.fc1_weight": "model-00001-of-00006.safetensors",
96
+ "esmc.transformer.blocks.14.ffn.fc2_weight": "model-00001-of-00006.safetensors",
97
+ "esmc.transformer.blocks.14.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
98
+ "esmc.transformer.blocks.14.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
99
+ "esmc.transformer.blocks.15.attn.k_ln.weight": "model-00001-of-00006.safetensors",
100
+ "esmc.transformer.blocks.15.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
101
+ "esmc.transformer.blocks.15.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
102
+ "esmc.transformer.blocks.15.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
103
+ "esmc.transformer.blocks.15.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
104
+ "esmc.transformer.blocks.15.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
105
+ "esmc.transformer.blocks.15.attn.out_proj.weight": "model-00001-of-00006.safetensors",
106
+ "esmc.transformer.blocks.15.attn.q_ln.weight": "model-00001-of-00006.safetensors",
107
+ "esmc.transformer.blocks.15.ffn._extra_state": "model-00001-of-00006.safetensors",
108
+ "esmc.transformer.blocks.15.ffn.fc1_weight": "model-00002-of-00006.safetensors",
109
+ "esmc.transformer.blocks.15.ffn.fc2_weight": "model-00002-of-00006.safetensors",
110
+ "esmc.transformer.blocks.15.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
111
+ "esmc.transformer.blocks.15.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
112
+ "esmc.transformer.blocks.16.attn.k_ln.weight": "model-00002-of-00006.safetensors",
113
+ "esmc.transformer.blocks.16.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
114
+ "esmc.transformer.blocks.16.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
115
+ "esmc.transformer.blocks.16.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
116
+ "esmc.transformer.blocks.16.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
117
+ "esmc.transformer.blocks.16.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
118
+ "esmc.transformer.blocks.16.attn.out_proj.weight": "model-00002-of-00006.safetensors",
119
+ "esmc.transformer.blocks.16.attn.q_ln.weight": "model-00002-of-00006.safetensors",
120
+ "esmc.transformer.blocks.16.ffn._extra_state": "model-00001-of-00006.safetensors",
121
+ "esmc.transformer.blocks.16.ffn.fc1_weight": "model-00002-of-00006.safetensors",
122
+ "esmc.transformer.blocks.16.ffn.fc2_weight": "model-00002-of-00006.safetensors",
123
+ "esmc.transformer.blocks.16.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
124
+ "esmc.transformer.blocks.16.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
125
+ "esmc.transformer.blocks.17.attn.k_ln.weight": "model-00002-of-00006.safetensors",
126
+ "esmc.transformer.blocks.17.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
127
+ "esmc.transformer.blocks.17.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
128
+ "esmc.transformer.blocks.17.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
129
+ "esmc.transformer.blocks.17.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
130
+ "esmc.transformer.blocks.17.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
131
+ "esmc.transformer.blocks.17.attn.out_proj.weight": "model-00002-of-00006.safetensors",
132
+ "esmc.transformer.blocks.17.attn.q_ln.weight": "model-00002-of-00006.safetensors",
133
+ "esmc.transformer.blocks.17.ffn._extra_state": "model-00001-of-00006.safetensors",
134
+ "esmc.transformer.blocks.17.ffn.fc1_weight": "model-00002-of-00006.safetensors",
135
+ "esmc.transformer.blocks.17.ffn.fc2_weight": "model-00002-of-00006.safetensors",
136
+ "esmc.transformer.blocks.17.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
137
+ "esmc.transformer.blocks.17.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
138
+ "esmc.transformer.blocks.18.attn.k_ln.weight": "model-00002-of-00006.safetensors",
139
+ "esmc.transformer.blocks.18.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
140
+ "esmc.transformer.blocks.18.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
141
+ "esmc.transformer.blocks.18.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
142
+ "esmc.transformer.blocks.18.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
143
+ "esmc.transformer.blocks.18.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
144
+ "esmc.transformer.blocks.18.attn.out_proj.weight": "model-00002-of-00006.safetensors",
145
+ "esmc.transformer.blocks.18.attn.q_ln.weight": "model-00002-of-00006.safetensors",
146
+ "esmc.transformer.blocks.18.ffn._extra_state": "model-00001-of-00006.safetensors",
147
+ "esmc.transformer.blocks.18.ffn.fc1_weight": "model-00002-of-00006.safetensors",
148
+ "esmc.transformer.blocks.18.ffn.fc2_weight": "model-00002-of-00006.safetensors",
149
+ "esmc.transformer.blocks.18.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
150
+ "esmc.transformer.blocks.18.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
151
+ "esmc.transformer.blocks.19.attn.k_ln.weight": "model-00002-of-00006.safetensors",
152
+ "esmc.transformer.blocks.19.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
153
+ "esmc.transformer.blocks.19.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
154
+ "esmc.transformer.blocks.19.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
155
+ "esmc.transformer.blocks.19.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
156
+ "esmc.transformer.blocks.19.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
157
+ "esmc.transformer.blocks.19.attn.out_proj.weight": "model-00002-of-00006.safetensors",
158
+ "esmc.transformer.blocks.19.attn.q_ln.weight": "model-00002-of-00006.safetensors",
159
+ "esmc.transformer.blocks.19.ffn._extra_state": "model-00001-of-00006.safetensors",
160
+ "esmc.transformer.blocks.19.ffn.fc1_weight": "model-00002-of-00006.safetensors",
161
+ "esmc.transformer.blocks.19.ffn.fc2_weight": "model-00002-of-00006.safetensors",
162
+ "esmc.transformer.blocks.19.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
163
+ "esmc.transformer.blocks.19.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
164
+ "esmc.transformer.blocks.2.attn.k_ln.weight": "model-00001-of-00006.safetensors",
165
+ "esmc.transformer.blocks.2.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
166
+ "esmc.transformer.blocks.2.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
167
+ "esmc.transformer.blocks.2.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
168
+ "esmc.transformer.blocks.2.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
169
+ "esmc.transformer.blocks.2.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
170
+ "esmc.transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00006.safetensors",
171
+ "esmc.transformer.blocks.2.attn.q_ln.weight": "model-00001-of-00006.safetensors",
172
+ "esmc.transformer.blocks.2.ffn._extra_state": "model-00001-of-00006.safetensors",
173
+ "esmc.transformer.blocks.2.ffn.fc1_weight": "model-00001-of-00006.safetensors",
174
+ "esmc.transformer.blocks.2.ffn.fc2_weight": "model-00001-of-00006.safetensors",
175
+ "esmc.transformer.blocks.2.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
176
+ "esmc.transformer.blocks.2.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
177
+ "esmc.transformer.blocks.20.attn.k_ln.weight": "model-00002-of-00006.safetensors",
178
+ "esmc.transformer.blocks.20.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
179
+ "esmc.transformer.blocks.20.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
180
+ "esmc.transformer.blocks.20.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
181
+ "esmc.transformer.blocks.20.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
182
+ "esmc.transformer.blocks.20.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
183
+ "esmc.transformer.blocks.20.attn.out_proj.weight": "model-00002-of-00006.safetensors",
184
+ "esmc.transformer.blocks.20.attn.q_ln.weight": "model-00002-of-00006.safetensors",
185
+ "esmc.transformer.blocks.20.ffn._extra_state": "model-00001-of-00006.safetensors",
186
+ "esmc.transformer.blocks.20.ffn.fc1_weight": "model-00002-of-00006.safetensors",
187
+ "esmc.transformer.blocks.20.ffn.fc2_weight": "model-00002-of-00006.safetensors",
188
+ "esmc.transformer.blocks.20.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
189
+ "esmc.transformer.blocks.20.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
190
+ "esmc.transformer.blocks.21.attn.k_ln.weight": "model-00002-of-00006.safetensors",
191
+ "esmc.transformer.blocks.21.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
192
+ "esmc.transformer.blocks.21.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
193
+ "esmc.transformer.blocks.21.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
194
+ "esmc.transformer.blocks.21.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
195
+ "esmc.transformer.blocks.21.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
196
+ "esmc.transformer.blocks.21.attn.out_proj.weight": "model-00002-of-00006.safetensors",
197
+ "esmc.transformer.blocks.21.attn.q_ln.weight": "model-00002-of-00006.safetensors",
198
+ "esmc.transformer.blocks.21.ffn._extra_state": "model-00001-of-00006.safetensors",
199
+ "esmc.transformer.blocks.21.ffn.fc1_weight": "model-00002-of-00006.safetensors",
200
+ "esmc.transformer.blocks.21.ffn.fc2_weight": "model-00002-of-00006.safetensors",
201
+ "esmc.transformer.blocks.21.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
202
+ "esmc.transformer.blocks.21.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
203
+ "esmc.transformer.blocks.22.attn.k_ln.weight": "model-00002-of-00006.safetensors",
204
+ "esmc.transformer.blocks.22.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
205
+ "esmc.transformer.blocks.22.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
206
+ "esmc.transformer.blocks.22.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
207
+ "esmc.transformer.blocks.22.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
208
+ "esmc.transformer.blocks.22.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
209
+ "esmc.transformer.blocks.22.attn.out_proj.weight": "model-00002-of-00006.safetensors",
210
+ "esmc.transformer.blocks.22.attn.q_ln.weight": "model-00002-of-00006.safetensors",
211
+ "esmc.transformer.blocks.22.ffn._extra_state": "model-00001-of-00006.safetensors",
212
+ "esmc.transformer.blocks.22.ffn.fc1_weight": "model-00002-of-00006.safetensors",
213
+ "esmc.transformer.blocks.22.ffn.fc2_weight": "model-00002-of-00006.safetensors",
214
+ "esmc.transformer.blocks.22.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
215
+ "esmc.transformer.blocks.22.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
216
+ "esmc.transformer.blocks.23.attn.k_ln.weight": "model-00002-of-00006.safetensors",
217
+ "esmc.transformer.blocks.23.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
218
+ "esmc.transformer.blocks.23.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
219
+ "esmc.transformer.blocks.23.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
220
+ "esmc.transformer.blocks.23.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
221
+ "esmc.transformer.blocks.23.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
222
+ "esmc.transformer.blocks.23.attn.out_proj.weight": "model-00002-of-00006.safetensors",
223
+ "esmc.transformer.blocks.23.attn.q_ln.weight": "model-00002-of-00006.safetensors",
224
+ "esmc.transformer.blocks.23.ffn._extra_state": "model-00001-of-00006.safetensors",
225
+ "esmc.transformer.blocks.23.ffn.fc1_weight": "model-00002-of-00006.safetensors",
226
+ "esmc.transformer.blocks.23.ffn.fc2_weight": "model-00002-of-00006.safetensors",
227
+ "esmc.transformer.blocks.23.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
228
+ "esmc.transformer.blocks.23.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
229
+ "esmc.transformer.blocks.24.attn.k_ln.weight": "model-00002-of-00006.safetensors",
230
+ "esmc.transformer.blocks.24.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
231
+ "esmc.transformer.blocks.24.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
232
+ "esmc.transformer.blocks.24.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
233
+ "esmc.transformer.blocks.24.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
234
+ "esmc.transformer.blocks.24.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
235
+ "esmc.transformer.blocks.24.attn.out_proj.weight": "model-00002-of-00006.safetensors",
236
+ "esmc.transformer.blocks.24.attn.q_ln.weight": "model-00002-of-00006.safetensors",
237
+ "esmc.transformer.blocks.24.ffn._extra_state": "model-00001-of-00006.safetensors",
238
+ "esmc.transformer.blocks.24.ffn.fc1_weight": "model-00002-of-00006.safetensors",
239
+ "esmc.transformer.blocks.24.ffn.fc2_weight": "model-00002-of-00006.safetensors",
240
+ "esmc.transformer.blocks.24.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
241
+ "esmc.transformer.blocks.24.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
242
+ "esmc.transformer.blocks.25.attn.k_ln.weight": "model-00002-of-00006.safetensors",
243
+ "esmc.transformer.blocks.25.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
244
+ "esmc.transformer.blocks.25.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
245
+ "esmc.transformer.blocks.25.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
246
+ "esmc.transformer.blocks.25.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
247
+ "esmc.transformer.blocks.25.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
248
+ "esmc.transformer.blocks.25.attn.out_proj.weight": "model-00002-of-00006.safetensors",
249
+ "esmc.transformer.blocks.25.attn.q_ln.weight": "model-00002-of-00006.safetensors",
250
+ "esmc.transformer.blocks.25.ffn._extra_state": "model-00001-of-00006.safetensors",
251
+ "esmc.transformer.blocks.25.ffn.fc1_weight": "model-00002-of-00006.safetensors",
252
+ "esmc.transformer.blocks.25.ffn.fc2_weight": "model-00002-of-00006.safetensors",
253
+ "esmc.transformer.blocks.25.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
254
+ "esmc.transformer.blocks.25.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
255
+ "esmc.transformer.blocks.26.attn.k_ln.weight": "model-00002-of-00006.safetensors",
256
+ "esmc.transformer.blocks.26.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
257
+ "esmc.transformer.blocks.26.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
258
+ "esmc.transformer.blocks.26.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
259
+ "esmc.transformer.blocks.26.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
260
+ "esmc.transformer.blocks.26.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
261
+ "esmc.transformer.blocks.26.attn.out_proj.weight": "model-00002-of-00006.safetensors",
262
+ "esmc.transformer.blocks.26.attn.q_ln.weight": "model-00002-of-00006.safetensors",
263
+ "esmc.transformer.blocks.26.ffn._extra_state": "model-00001-of-00006.safetensors",
264
+ "esmc.transformer.blocks.26.ffn.fc1_weight": "model-00002-of-00006.safetensors",
265
+ "esmc.transformer.blocks.26.ffn.fc2_weight": "model-00002-of-00006.safetensors",
266
+ "esmc.transformer.blocks.26.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
267
+ "esmc.transformer.blocks.26.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
268
+ "esmc.transformer.blocks.27.attn.k_ln.weight": "model-00002-of-00006.safetensors",
269
+ "esmc.transformer.blocks.27.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
270
+ "esmc.transformer.blocks.27.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
271
+ "esmc.transformer.blocks.27.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
272
+ "esmc.transformer.blocks.27.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
273
+ "esmc.transformer.blocks.27.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
274
+ "esmc.transformer.blocks.27.attn.out_proj.weight": "model-00002-of-00006.safetensors",
275
+ "esmc.transformer.blocks.27.attn.q_ln.weight": "model-00002-of-00006.safetensors",
276
+ "esmc.transformer.blocks.27.ffn._extra_state": "model-00001-of-00006.safetensors",
277
+ "esmc.transformer.blocks.27.ffn.fc1_weight": "model-00002-of-00006.safetensors",
278
+ "esmc.transformer.blocks.27.ffn.fc2_weight": "model-00002-of-00006.safetensors",
279
+ "esmc.transformer.blocks.27.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
280
+ "esmc.transformer.blocks.27.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
281
+ "esmc.transformer.blocks.28.attn.k_ln.weight": "model-00002-of-00006.safetensors",
282
+ "esmc.transformer.blocks.28.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
283
+ "esmc.transformer.blocks.28.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
284
+ "esmc.transformer.blocks.28.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
285
+ "esmc.transformer.blocks.28.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
286
+ "esmc.transformer.blocks.28.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
287
+ "esmc.transformer.blocks.28.attn.out_proj.weight": "model-00002-of-00006.safetensors",
288
+ "esmc.transformer.blocks.28.attn.q_ln.weight": "model-00002-of-00006.safetensors",
289
+ "esmc.transformer.blocks.28.ffn._extra_state": "model-00001-of-00006.safetensors",
290
+ "esmc.transformer.blocks.28.ffn.fc1_weight": "model-00002-of-00006.safetensors",
291
+ "esmc.transformer.blocks.28.ffn.fc2_weight": "model-00002-of-00006.safetensors",
292
+ "esmc.transformer.blocks.28.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
293
+ "esmc.transformer.blocks.28.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
294
+ "esmc.transformer.blocks.29.attn.k_ln.weight": "model-00002-of-00006.safetensors",
295
+ "esmc.transformer.blocks.29.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
296
+ "esmc.transformer.blocks.29.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
297
+ "esmc.transformer.blocks.29.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
298
+ "esmc.transformer.blocks.29.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
299
+ "esmc.transformer.blocks.29.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
300
+ "esmc.transformer.blocks.29.attn.out_proj.weight": "model-00002-of-00006.safetensors",
301
+ "esmc.transformer.blocks.29.attn.q_ln.weight": "model-00002-of-00006.safetensors",
302
+ "esmc.transformer.blocks.29.ffn._extra_state": "model-00001-of-00006.safetensors",
303
+ "esmc.transformer.blocks.29.ffn.fc1_weight": "model-00002-of-00006.safetensors",
304
+ "esmc.transformer.blocks.29.ffn.fc2_weight": "model-00002-of-00006.safetensors",
305
+ "esmc.transformer.blocks.29.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
306
+ "esmc.transformer.blocks.29.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
307
+ "esmc.transformer.blocks.3.attn.k_ln.weight": "model-00001-of-00006.safetensors",
308
+ "esmc.transformer.blocks.3.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
309
+ "esmc.transformer.blocks.3.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
310
+ "esmc.transformer.blocks.3.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
311
+ "esmc.transformer.blocks.3.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
312
+ "esmc.transformer.blocks.3.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
313
+ "esmc.transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00006.safetensors",
314
+ "esmc.transformer.blocks.3.attn.q_ln.weight": "model-00001-of-00006.safetensors",
315
+ "esmc.transformer.blocks.3.ffn._extra_state": "model-00001-of-00006.safetensors",
316
+ "esmc.transformer.blocks.3.ffn.fc1_weight": "model-00001-of-00006.safetensors",
317
+ "esmc.transformer.blocks.3.ffn.fc2_weight": "model-00001-of-00006.safetensors",
318
+ "esmc.transformer.blocks.3.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
319
+ "esmc.transformer.blocks.3.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
320
+ "esmc.transformer.blocks.30.attn.k_ln.weight": "model-00002-of-00006.safetensors",
321
+ "esmc.transformer.blocks.30.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
322
+ "esmc.transformer.blocks.30.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
323
+ "esmc.transformer.blocks.30.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
324
+ "esmc.transformer.blocks.30.attn.layernorm_qkv.weight": "model-00002-of-00006.safetensors",
325
+ "esmc.transformer.blocks.30.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
326
+ "esmc.transformer.blocks.30.attn.out_proj.weight": "model-00002-of-00006.safetensors",
327
+ "esmc.transformer.blocks.30.attn.q_ln.weight": "model-00002-of-00006.safetensors",
328
+ "esmc.transformer.blocks.30.ffn._extra_state": "model-00001-of-00006.safetensors",
329
+ "esmc.transformer.blocks.30.ffn.fc1_weight": "model-00002-of-00006.safetensors",
330
+ "esmc.transformer.blocks.30.ffn.fc2_weight": "model-00002-of-00006.safetensors",
331
+ "esmc.transformer.blocks.30.ffn.layer_norm_bias": "model-00002-of-00006.safetensors",
332
+ "esmc.transformer.blocks.30.ffn.layer_norm_weight": "model-00002-of-00006.safetensors",
333
+ "esmc.transformer.blocks.31.attn.k_ln.weight": "model-00003-of-00006.safetensors",
334
+ "esmc.transformer.blocks.31.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
335
+ "esmc.transformer.blocks.31.attn.layernorm_qkv.layer_norm_bias": "model-00002-of-00006.safetensors",
336
+ "esmc.transformer.blocks.31.attn.layernorm_qkv.layer_norm_weight": "model-00002-of-00006.safetensors",
337
+ "esmc.transformer.blocks.31.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
338
+ "esmc.transformer.blocks.31.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
339
+ "esmc.transformer.blocks.31.attn.out_proj.weight": "model-00003-of-00006.safetensors",
340
+ "esmc.transformer.blocks.31.attn.q_ln.weight": "model-00003-of-00006.safetensors",
341
+ "esmc.transformer.blocks.31.ffn._extra_state": "model-00001-of-00006.safetensors",
342
+ "esmc.transformer.blocks.31.ffn.fc1_weight": "model-00003-of-00006.safetensors",
343
+ "esmc.transformer.blocks.31.ffn.fc2_weight": "model-00003-of-00006.safetensors",
344
+ "esmc.transformer.blocks.31.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
345
+ "esmc.transformer.blocks.31.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
346
+ "esmc.transformer.blocks.32.attn.k_ln.weight": "model-00003-of-00006.safetensors",
347
+ "esmc.transformer.blocks.32.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
348
+ "esmc.transformer.blocks.32.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
349
+ "esmc.transformer.blocks.32.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
350
+ "esmc.transformer.blocks.32.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
351
+ "esmc.transformer.blocks.32.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
352
+ "esmc.transformer.blocks.32.attn.out_proj.weight": "model-00003-of-00006.safetensors",
353
+ "esmc.transformer.blocks.32.attn.q_ln.weight": "model-00003-of-00006.safetensors",
354
+ "esmc.transformer.blocks.32.ffn._extra_state": "model-00001-of-00006.safetensors",
355
+ "esmc.transformer.blocks.32.ffn.fc1_weight": "model-00003-of-00006.safetensors",
356
+ "esmc.transformer.blocks.32.ffn.fc2_weight": "model-00003-of-00006.safetensors",
357
+ "esmc.transformer.blocks.32.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
358
+ "esmc.transformer.blocks.32.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
359
+ "esmc.transformer.blocks.33.attn.k_ln.weight": "model-00003-of-00006.safetensors",
360
+ "esmc.transformer.blocks.33.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
361
+ "esmc.transformer.blocks.33.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
362
+ "esmc.transformer.blocks.33.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
363
+ "esmc.transformer.blocks.33.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
364
+ "esmc.transformer.blocks.33.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
365
+ "esmc.transformer.blocks.33.attn.out_proj.weight": "model-00003-of-00006.safetensors",
366
+ "esmc.transformer.blocks.33.attn.q_ln.weight": "model-00003-of-00006.safetensors",
367
+ "esmc.transformer.blocks.33.ffn._extra_state": "model-00001-of-00006.safetensors",
368
+ "esmc.transformer.blocks.33.ffn.fc1_weight": "model-00003-of-00006.safetensors",
369
+ "esmc.transformer.blocks.33.ffn.fc2_weight": "model-00003-of-00006.safetensors",
370
+ "esmc.transformer.blocks.33.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
371
+ "esmc.transformer.blocks.33.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
372
+ "esmc.transformer.blocks.34.attn.k_ln.weight": "model-00003-of-00006.safetensors",
373
+ "esmc.transformer.blocks.34.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
374
+ "esmc.transformer.blocks.34.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
375
+ "esmc.transformer.blocks.34.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
376
+ "esmc.transformer.blocks.34.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
377
+ "esmc.transformer.blocks.34.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
378
+ "esmc.transformer.blocks.34.attn.out_proj.weight": "model-00003-of-00006.safetensors",
379
+ "esmc.transformer.blocks.34.attn.q_ln.weight": "model-00003-of-00006.safetensors",
380
+ "esmc.transformer.blocks.34.ffn._extra_state": "model-00001-of-00006.safetensors",
381
+ "esmc.transformer.blocks.34.ffn.fc1_weight": "model-00003-of-00006.safetensors",
382
+ "esmc.transformer.blocks.34.ffn.fc2_weight": "model-00003-of-00006.safetensors",
383
+ "esmc.transformer.blocks.34.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
384
+ "esmc.transformer.blocks.34.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
385
+ "esmc.transformer.blocks.35.attn.k_ln.weight": "model-00003-of-00006.safetensors",
386
+ "esmc.transformer.blocks.35.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
387
+ "esmc.transformer.blocks.35.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
388
+ "esmc.transformer.blocks.35.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
389
+ "esmc.transformer.blocks.35.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
390
+ "esmc.transformer.blocks.35.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
391
+ "esmc.transformer.blocks.35.attn.out_proj.weight": "model-00003-of-00006.safetensors",
392
+ "esmc.transformer.blocks.35.attn.q_ln.weight": "model-00003-of-00006.safetensors",
393
+ "esmc.transformer.blocks.35.ffn._extra_state": "model-00001-of-00006.safetensors",
394
+ "esmc.transformer.blocks.35.ffn.fc1_weight": "model-00003-of-00006.safetensors",
395
+ "esmc.transformer.blocks.35.ffn.fc2_weight": "model-00003-of-00006.safetensors",
396
+ "esmc.transformer.blocks.35.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
397
+ "esmc.transformer.blocks.35.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
398
+ "esmc.transformer.blocks.36.attn.k_ln.weight": "model-00003-of-00006.safetensors",
399
+ "esmc.transformer.blocks.36.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
400
+ "esmc.transformer.blocks.36.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
401
+ "esmc.transformer.blocks.36.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
402
+ "esmc.transformer.blocks.36.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
403
+ "esmc.transformer.blocks.36.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
404
+ "esmc.transformer.blocks.36.attn.out_proj.weight": "model-00003-of-00006.safetensors",
405
+ "esmc.transformer.blocks.36.attn.q_ln.weight": "model-00003-of-00006.safetensors",
406
+ "esmc.transformer.blocks.36.ffn._extra_state": "model-00001-of-00006.safetensors",
407
+ "esmc.transformer.blocks.36.ffn.fc1_weight": "model-00003-of-00006.safetensors",
408
+ "esmc.transformer.blocks.36.ffn.fc2_weight": "model-00003-of-00006.safetensors",
409
+ "esmc.transformer.blocks.36.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
410
+ "esmc.transformer.blocks.36.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
411
+ "esmc.transformer.blocks.37.attn.k_ln.weight": "model-00003-of-00006.safetensors",
412
+ "esmc.transformer.blocks.37.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
413
+ "esmc.transformer.blocks.37.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
414
+ "esmc.transformer.blocks.37.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
415
+ "esmc.transformer.blocks.37.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
416
+ "esmc.transformer.blocks.37.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
417
+ "esmc.transformer.blocks.37.attn.out_proj.weight": "model-00003-of-00006.safetensors",
418
+ "esmc.transformer.blocks.37.attn.q_ln.weight": "model-00003-of-00006.safetensors",
419
+ "esmc.transformer.blocks.37.ffn._extra_state": "model-00001-of-00006.safetensors",
420
+ "esmc.transformer.blocks.37.ffn.fc1_weight": "model-00003-of-00006.safetensors",
421
+ "esmc.transformer.blocks.37.ffn.fc2_weight": "model-00003-of-00006.safetensors",
422
+ "esmc.transformer.blocks.37.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
423
+ "esmc.transformer.blocks.37.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
424
+ "esmc.transformer.blocks.38.attn.k_ln.weight": "model-00003-of-00006.safetensors",
425
+ "esmc.transformer.blocks.38.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
426
+ "esmc.transformer.blocks.38.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
427
+ "esmc.transformer.blocks.38.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
428
+ "esmc.transformer.blocks.38.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
429
+ "esmc.transformer.blocks.38.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
430
+ "esmc.transformer.blocks.38.attn.out_proj.weight": "model-00003-of-00006.safetensors",
431
+ "esmc.transformer.blocks.38.attn.q_ln.weight": "model-00003-of-00006.safetensors",
432
+ "esmc.transformer.blocks.38.ffn._extra_state": "model-00001-of-00006.safetensors",
433
+ "esmc.transformer.blocks.38.ffn.fc1_weight": "model-00003-of-00006.safetensors",
434
+ "esmc.transformer.blocks.38.ffn.fc2_weight": "model-00003-of-00006.safetensors",
435
+ "esmc.transformer.blocks.38.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
436
+ "esmc.transformer.blocks.38.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
437
+ "esmc.transformer.blocks.39.attn.k_ln.weight": "model-00003-of-00006.safetensors",
438
+ "esmc.transformer.blocks.39.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
439
+ "esmc.transformer.blocks.39.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
440
+ "esmc.transformer.blocks.39.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
441
+ "esmc.transformer.blocks.39.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
442
+ "esmc.transformer.blocks.39.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
443
+ "esmc.transformer.blocks.39.attn.out_proj.weight": "model-00003-of-00006.safetensors",
444
+ "esmc.transformer.blocks.39.attn.q_ln.weight": "model-00003-of-00006.safetensors",
445
+ "esmc.transformer.blocks.39.ffn._extra_state": "model-00001-of-00006.safetensors",
446
+ "esmc.transformer.blocks.39.ffn.fc1_weight": "model-00003-of-00006.safetensors",
447
+ "esmc.transformer.blocks.39.ffn.fc2_weight": "model-00003-of-00006.safetensors",
448
+ "esmc.transformer.blocks.39.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
449
+ "esmc.transformer.blocks.39.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
450
+ "esmc.transformer.blocks.4.attn.k_ln.weight": "model-00001-of-00006.safetensors",
451
+ "esmc.transformer.blocks.4.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
452
+ "esmc.transformer.blocks.4.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
453
+ "esmc.transformer.blocks.4.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
454
+ "esmc.transformer.blocks.4.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
455
+ "esmc.transformer.blocks.4.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
456
+ "esmc.transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00006.safetensors",
457
+ "esmc.transformer.blocks.4.attn.q_ln.weight": "model-00001-of-00006.safetensors",
458
+ "esmc.transformer.blocks.4.ffn._extra_state": "model-00001-of-00006.safetensors",
459
+ "esmc.transformer.blocks.4.ffn.fc1_weight": "model-00001-of-00006.safetensors",
460
+ "esmc.transformer.blocks.4.ffn.fc2_weight": "model-00001-of-00006.safetensors",
461
+ "esmc.transformer.blocks.4.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
462
+ "esmc.transformer.blocks.4.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
463
+ "esmc.transformer.blocks.40.attn.k_ln.weight": "model-00003-of-00006.safetensors",
464
+ "esmc.transformer.blocks.40.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
465
+ "esmc.transformer.blocks.40.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
466
+ "esmc.transformer.blocks.40.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
467
+ "esmc.transformer.blocks.40.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
468
+ "esmc.transformer.blocks.40.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
469
+ "esmc.transformer.blocks.40.attn.out_proj.weight": "model-00003-of-00006.safetensors",
470
+ "esmc.transformer.blocks.40.attn.q_ln.weight": "model-00003-of-00006.safetensors",
471
+ "esmc.transformer.blocks.40.ffn._extra_state": "model-00001-of-00006.safetensors",
472
+ "esmc.transformer.blocks.40.ffn.fc1_weight": "model-00003-of-00006.safetensors",
473
+ "esmc.transformer.blocks.40.ffn.fc2_weight": "model-00003-of-00006.safetensors",
474
+ "esmc.transformer.blocks.40.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
475
+ "esmc.transformer.blocks.40.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
476
+ "esmc.transformer.blocks.41.attn.k_ln.weight": "model-00003-of-00006.safetensors",
477
+ "esmc.transformer.blocks.41.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
478
+ "esmc.transformer.blocks.41.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
479
+ "esmc.transformer.blocks.41.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
480
+ "esmc.transformer.blocks.41.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
481
+ "esmc.transformer.blocks.41.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
482
+ "esmc.transformer.blocks.41.attn.out_proj.weight": "model-00003-of-00006.safetensors",
483
+ "esmc.transformer.blocks.41.attn.q_ln.weight": "model-00003-of-00006.safetensors",
484
+ "esmc.transformer.blocks.41.ffn._extra_state": "model-00001-of-00006.safetensors",
485
+ "esmc.transformer.blocks.41.ffn.fc1_weight": "model-00003-of-00006.safetensors",
486
+ "esmc.transformer.blocks.41.ffn.fc2_weight": "model-00003-of-00006.safetensors",
487
+ "esmc.transformer.blocks.41.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
488
+ "esmc.transformer.blocks.41.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
489
+ "esmc.transformer.blocks.42.attn.k_ln.weight": "model-00003-of-00006.safetensors",
490
+ "esmc.transformer.blocks.42.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
491
+ "esmc.transformer.blocks.42.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
492
+ "esmc.transformer.blocks.42.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
493
+ "esmc.transformer.blocks.42.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
494
+ "esmc.transformer.blocks.42.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
495
+ "esmc.transformer.blocks.42.attn.out_proj.weight": "model-00003-of-00006.safetensors",
496
+ "esmc.transformer.blocks.42.attn.q_ln.weight": "model-00003-of-00006.safetensors",
497
+ "esmc.transformer.blocks.42.ffn._extra_state": "model-00001-of-00006.safetensors",
498
+ "esmc.transformer.blocks.42.ffn.fc1_weight": "model-00003-of-00006.safetensors",
499
+ "esmc.transformer.blocks.42.ffn.fc2_weight": "model-00003-of-00006.safetensors",
500
+ "esmc.transformer.blocks.42.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
501
+ "esmc.transformer.blocks.42.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
502
+ "esmc.transformer.blocks.43.attn.k_ln.weight": "model-00003-of-00006.safetensors",
503
+ "esmc.transformer.blocks.43.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
504
+ "esmc.transformer.blocks.43.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
505
+ "esmc.transformer.blocks.43.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
506
+ "esmc.transformer.blocks.43.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
507
+ "esmc.transformer.blocks.43.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
508
+ "esmc.transformer.blocks.43.attn.out_proj.weight": "model-00003-of-00006.safetensors",
509
+ "esmc.transformer.blocks.43.attn.q_ln.weight": "model-00003-of-00006.safetensors",
510
+ "esmc.transformer.blocks.43.ffn._extra_state": "model-00001-of-00006.safetensors",
511
+ "esmc.transformer.blocks.43.ffn.fc1_weight": "model-00003-of-00006.safetensors",
512
+ "esmc.transformer.blocks.43.ffn.fc2_weight": "model-00003-of-00006.safetensors",
513
+ "esmc.transformer.blocks.43.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
514
+ "esmc.transformer.blocks.43.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
515
+ "esmc.transformer.blocks.44.attn.k_ln.weight": "model-00003-of-00006.safetensors",
516
+ "esmc.transformer.blocks.44.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
517
+ "esmc.transformer.blocks.44.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
518
+ "esmc.transformer.blocks.44.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
519
+ "esmc.transformer.blocks.44.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
520
+ "esmc.transformer.blocks.44.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
521
+ "esmc.transformer.blocks.44.attn.out_proj.weight": "model-00003-of-00006.safetensors",
522
+ "esmc.transformer.blocks.44.attn.q_ln.weight": "model-00003-of-00006.safetensors",
523
+ "esmc.transformer.blocks.44.ffn._extra_state": "model-00001-of-00006.safetensors",
524
+ "esmc.transformer.blocks.44.ffn.fc1_weight": "model-00003-of-00006.safetensors",
525
+ "esmc.transformer.blocks.44.ffn.fc2_weight": "model-00003-of-00006.safetensors",
526
+ "esmc.transformer.blocks.44.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
527
+ "esmc.transformer.blocks.44.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
528
+ "esmc.transformer.blocks.45.attn.k_ln.weight": "model-00003-of-00006.safetensors",
529
+ "esmc.transformer.blocks.45.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
530
+ "esmc.transformer.blocks.45.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
531
+ "esmc.transformer.blocks.45.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
532
+ "esmc.transformer.blocks.45.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
533
+ "esmc.transformer.blocks.45.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
534
+ "esmc.transformer.blocks.45.attn.out_proj.weight": "model-00003-of-00006.safetensors",
535
+ "esmc.transformer.blocks.45.attn.q_ln.weight": "model-00003-of-00006.safetensors",
536
+ "esmc.transformer.blocks.45.ffn._extra_state": "model-00001-of-00006.safetensors",
537
+ "esmc.transformer.blocks.45.ffn.fc1_weight": "model-00003-of-00006.safetensors",
538
+ "esmc.transformer.blocks.45.ffn.fc2_weight": "model-00003-of-00006.safetensors",
539
+ "esmc.transformer.blocks.45.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
540
+ "esmc.transformer.blocks.45.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
541
+ "esmc.transformer.blocks.46.attn.k_ln.weight": "model-00003-of-00006.safetensors",
542
+ "esmc.transformer.blocks.46.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
543
+ "esmc.transformer.blocks.46.attn.layernorm_qkv.layer_norm_bias": "model-00003-of-00006.safetensors",
544
+ "esmc.transformer.blocks.46.attn.layernorm_qkv.layer_norm_weight": "model-00003-of-00006.safetensors",
545
+ "esmc.transformer.blocks.46.attn.layernorm_qkv.weight": "model-00003-of-00006.safetensors",
546
+ "esmc.transformer.blocks.46.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
547
+ "esmc.transformer.blocks.46.attn.out_proj.weight": "model-00003-of-00006.safetensors",
548
+ "esmc.transformer.blocks.46.attn.q_ln.weight": "model-00003-of-00006.safetensors",
549
+ "esmc.transformer.blocks.46.ffn._extra_state": "model-00001-of-00006.safetensors",
550
+ "esmc.transformer.blocks.46.ffn.fc1_weight": "model-00004-of-00006.safetensors",
551
+ "esmc.transformer.blocks.46.ffn.fc2_weight": "model-00004-of-00006.safetensors",
552
+ "esmc.transformer.blocks.46.ffn.layer_norm_bias": "model-00003-of-00006.safetensors",
553
+ "esmc.transformer.blocks.46.ffn.layer_norm_weight": "model-00003-of-00006.safetensors",
554
+ "esmc.transformer.blocks.47.attn.k_ln.weight": "model-00004-of-00006.safetensors",
555
+ "esmc.transformer.blocks.47.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
556
+ "esmc.transformer.blocks.47.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
557
+ "esmc.transformer.blocks.47.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
558
+ "esmc.transformer.blocks.47.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
559
+ "esmc.transformer.blocks.47.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
560
+ "esmc.transformer.blocks.47.attn.out_proj.weight": "model-00004-of-00006.safetensors",
561
+ "esmc.transformer.blocks.47.attn.q_ln.weight": "model-00004-of-00006.safetensors",
562
+ "esmc.transformer.blocks.47.ffn._extra_state": "model-00001-of-00006.safetensors",
563
+ "esmc.transformer.blocks.47.ffn.fc1_weight": "model-00004-of-00006.safetensors",
564
+ "esmc.transformer.blocks.47.ffn.fc2_weight": "model-00004-of-00006.safetensors",
565
+ "esmc.transformer.blocks.47.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
566
+ "esmc.transformer.blocks.47.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
567
+ "esmc.transformer.blocks.48.attn.k_ln.weight": "model-00004-of-00006.safetensors",
568
+ "esmc.transformer.blocks.48.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
569
+ "esmc.transformer.blocks.48.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
570
+ "esmc.transformer.blocks.48.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
571
+ "esmc.transformer.blocks.48.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
572
+ "esmc.transformer.blocks.48.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
573
+ "esmc.transformer.blocks.48.attn.out_proj.weight": "model-00004-of-00006.safetensors",
574
+ "esmc.transformer.blocks.48.attn.q_ln.weight": "model-00004-of-00006.safetensors",
575
+ "esmc.transformer.blocks.48.ffn._extra_state": "model-00001-of-00006.safetensors",
576
+ "esmc.transformer.blocks.48.ffn.fc1_weight": "model-00004-of-00006.safetensors",
577
+ "esmc.transformer.blocks.48.ffn.fc2_weight": "model-00004-of-00006.safetensors",
578
+ "esmc.transformer.blocks.48.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
579
+ "esmc.transformer.blocks.48.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
580
+ "esmc.transformer.blocks.49.attn.k_ln.weight": "model-00004-of-00006.safetensors",
581
+ "esmc.transformer.blocks.49.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
582
+ "esmc.transformer.blocks.49.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
583
+ "esmc.transformer.blocks.49.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
584
+ "esmc.transformer.blocks.49.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
585
+ "esmc.transformer.blocks.49.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
586
+ "esmc.transformer.blocks.49.attn.out_proj.weight": "model-00004-of-00006.safetensors",
587
+ "esmc.transformer.blocks.49.attn.q_ln.weight": "model-00004-of-00006.safetensors",
588
+ "esmc.transformer.blocks.49.ffn._extra_state": "model-00001-of-00006.safetensors",
589
+ "esmc.transformer.blocks.49.ffn.fc1_weight": "model-00004-of-00006.safetensors",
590
+ "esmc.transformer.blocks.49.ffn.fc2_weight": "model-00004-of-00006.safetensors",
591
+ "esmc.transformer.blocks.49.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
592
+ "esmc.transformer.blocks.49.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
593
+ "esmc.transformer.blocks.5.attn.k_ln.weight": "model-00001-of-00006.safetensors",
594
+ "esmc.transformer.blocks.5.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
595
+ "esmc.transformer.blocks.5.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
596
+ "esmc.transformer.blocks.5.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
597
+ "esmc.transformer.blocks.5.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
598
+ "esmc.transformer.blocks.5.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
599
+ "esmc.transformer.blocks.5.attn.out_proj.weight": "model-00001-of-00006.safetensors",
600
+ "esmc.transformer.blocks.5.attn.q_ln.weight": "model-00001-of-00006.safetensors",
601
+ "esmc.transformer.blocks.5.ffn._extra_state": "model-00001-of-00006.safetensors",
602
+ "esmc.transformer.blocks.5.ffn.fc1_weight": "model-00001-of-00006.safetensors",
603
+ "esmc.transformer.blocks.5.ffn.fc2_weight": "model-00001-of-00006.safetensors",
604
+ "esmc.transformer.blocks.5.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
605
+ "esmc.transformer.blocks.5.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
606
+ "esmc.transformer.blocks.50.attn.k_ln.weight": "model-00004-of-00006.safetensors",
607
+ "esmc.transformer.blocks.50.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
608
+ "esmc.transformer.blocks.50.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
609
+ "esmc.transformer.blocks.50.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
610
+ "esmc.transformer.blocks.50.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
611
+ "esmc.transformer.blocks.50.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
612
+ "esmc.transformer.blocks.50.attn.out_proj.weight": "model-00004-of-00006.safetensors",
613
+ "esmc.transformer.blocks.50.attn.q_ln.weight": "model-00004-of-00006.safetensors",
614
+ "esmc.transformer.blocks.50.ffn._extra_state": "model-00001-of-00006.safetensors",
615
+ "esmc.transformer.blocks.50.ffn.fc1_weight": "model-00004-of-00006.safetensors",
616
+ "esmc.transformer.blocks.50.ffn.fc2_weight": "model-00004-of-00006.safetensors",
617
+ "esmc.transformer.blocks.50.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
618
+ "esmc.transformer.blocks.50.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
619
+ "esmc.transformer.blocks.51.attn.k_ln.weight": "model-00004-of-00006.safetensors",
620
+ "esmc.transformer.blocks.51.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
621
+ "esmc.transformer.blocks.51.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
622
+ "esmc.transformer.blocks.51.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
623
+ "esmc.transformer.blocks.51.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
624
+ "esmc.transformer.blocks.51.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
625
+ "esmc.transformer.blocks.51.attn.out_proj.weight": "model-00004-of-00006.safetensors",
626
+ "esmc.transformer.blocks.51.attn.q_ln.weight": "model-00004-of-00006.safetensors",
627
+ "esmc.transformer.blocks.51.ffn._extra_state": "model-00001-of-00006.safetensors",
628
+ "esmc.transformer.blocks.51.ffn.fc1_weight": "model-00004-of-00006.safetensors",
629
+ "esmc.transformer.blocks.51.ffn.fc2_weight": "model-00004-of-00006.safetensors",
630
+ "esmc.transformer.blocks.51.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
631
+ "esmc.transformer.blocks.51.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
632
+ "esmc.transformer.blocks.52.attn.k_ln.weight": "model-00004-of-00006.safetensors",
633
+ "esmc.transformer.blocks.52.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
634
+ "esmc.transformer.blocks.52.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
635
+ "esmc.transformer.blocks.52.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
636
+ "esmc.transformer.blocks.52.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
637
+ "esmc.transformer.blocks.52.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
638
+ "esmc.transformer.blocks.52.attn.out_proj.weight": "model-00004-of-00006.safetensors",
639
+ "esmc.transformer.blocks.52.attn.q_ln.weight": "model-00004-of-00006.safetensors",
640
+ "esmc.transformer.blocks.52.ffn._extra_state": "model-00001-of-00006.safetensors",
641
+ "esmc.transformer.blocks.52.ffn.fc1_weight": "model-00004-of-00006.safetensors",
642
+ "esmc.transformer.blocks.52.ffn.fc2_weight": "model-00004-of-00006.safetensors",
643
+ "esmc.transformer.blocks.52.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
644
+ "esmc.transformer.blocks.52.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
645
+ "esmc.transformer.blocks.53.attn.k_ln.weight": "model-00004-of-00006.safetensors",
646
+ "esmc.transformer.blocks.53.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
647
+ "esmc.transformer.blocks.53.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
648
+ "esmc.transformer.blocks.53.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
649
+ "esmc.transformer.blocks.53.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
650
+ "esmc.transformer.blocks.53.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
651
+ "esmc.transformer.blocks.53.attn.out_proj.weight": "model-00004-of-00006.safetensors",
652
+ "esmc.transformer.blocks.53.attn.q_ln.weight": "model-00004-of-00006.safetensors",
653
+ "esmc.transformer.blocks.53.ffn._extra_state": "model-00001-of-00006.safetensors",
654
+ "esmc.transformer.blocks.53.ffn.fc1_weight": "model-00004-of-00006.safetensors",
655
+ "esmc.transformer.blocks.53.ffn.fc2_weight": "model-00004-of-00006.safetensors",
656
+ "esmc.transformer.blocks.53.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
657
+ "esmc.transformer.blocks.53.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
658
+ "esmc.transformer.blocks.54.attn.k_ln.weight": "model-00004-of-00006.safetensors",
659
+ "esmc.transformer.blocks.54.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
660
+ "esmc.transformer.blocks.54.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
661
+ "esmc.transformer.blocks.54.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
662
+ "esmc.transformer.blocks.54.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
663
+ "esmc.transformer.blocks.54.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
664
+ "esmc.transformer.blocks.54.attn.out_proj.weight": "model-00004-of-00006.safetensors",
665
+ "esmc.transformer.blocks.54.attn.q_ln.weight": "model-00004-of-00006.safetensors",
666
+ "esmc.transformer.blocks.54.ffn._extra_state": "model-00001-of-00006.safetensors",
667
+ "esmc.transformer.blocks.54.ffn.fc1_weight": "model-00004-of-00006.safetensors",
668
+ "esmc.transformer.blocks.54.ffn.fc2_weight": "model-00004-of-00006.safetensors",
669
+ "esmc.transformer.blocks.54.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
670
+ "esmc.transformer.blocks.54.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
671
+ "esmc.transformer.blocks.55.attn.k_ln.weight": "model-00004-of-00006.safetensors",
672
+ "esmc.transformer.blocks.55.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
673
+ "esmc.transformer.blocks.55.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
674
+ "esmc.transformer.blocks.55.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
675
+ "esmc.transformer.blocks.55.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
676
+ "esmc.transformer.blocks.55.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
677
+ "esmc.transformer.blocks.55.attn.out_proj.weight": "model-00004-of-00006.safetensors",
678
+ "esmc.transformer.blocks.55.attn.q_ln.weight": "model-00004-of-00006.safetensors",
679
+ "esmc.transformer.blocks.55.ffn._extra_state": "model-00001-of-00006.safetensors",
680
+ "esmc.transformer.blocks.55.ffn.fc1_weight": "model-00004-of-00006.safetensors",
681
+ "esmc.transformer.blocks.55.ffn.fc2_weight": "model-00004-of-00006.safetensors",
682
+ "esmc.transformer.blocks.55.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
683
+ "esmc.transformer.blocks.55.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
684
+ "esmc.transformer.blocks.56.attn.k_ln.weight": "model-00004-of-00006.safetensors",
685
+ "esmc.transformer.blocks.56.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
686
+ "esmc.transformer.blocks.56.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
687
+ "esmc.transformer.blocks.56.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
688
+ "esmc.transformer.blocks.56.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
689
+ "esmc.transformer.blocks.56.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
690
+ "esmc.transformer.blocks.56.attn.out_proj.weight": "model-00004-of-00006.safetensors",
691
+ "esmc.transformer.blocks.56.attn.q_ln.weight": "model-00004-of-00006.safetensors",
692
+ "esmc.transformer.blocks.56.ffn._extra_state": "model-00001-of-00006.safetensors",
693
+ "esmc.transformer.blocks.56.ffn.fc1_weight": "model-00004-of-00006.safetensors",
694
+ "esmc.transformer.blocks.56.ffn.fc2_weight": "model-00004-of-00006.safetensors",
695
+ "esmc.transformer.blocks.56.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
696
+ "esmc.transformer.blocks.56.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
697
+ "esmc.transformer.blocks.57.attn.k_ln.weight": "model-00004-of-00006.safetensors",
698
+ "esmc.transformer.blocks.57.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
699
+ "esmc.transformer.blocks.57.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
700
+ "esmc.transformer.blocks.57.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
701
+ "esmc.transformer.blocks.57.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
702
+ "esmc.transformer.blocks.57.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
703
+ "esmc.transformer.blocks.57.attn.out_proj.weight": "model-00004-of-00006.safetensors",
704
+ "esmc.transformer.blocks.57.attn.q_ln.weight": "model-00004-of-00006.safetensors",
705
+ "esmc.transformer.blocks.57.ffn._extra_state": "model-00001-of-00006.safetensors",
706
+ "esmc.transformer.blocks.57.ffn.fc1_weight": "model-00004-of-00006.safetensors",
707
+ "esmc.transformer.blocks.57.ffn.fc2_weight": "model-00004-of-00006.safetensors",
708
+ "esmc.transformer.blocks.57.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
709
+ "esmc.transformer.blocks.57.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
710
+ "esmc.transformer.blocks.58.attn.k_ln.weight": "model-00004-of-00006.safetensors",
711
+ "esmc.transformer.blocks.58.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
712
+ "esmc.transformer.blocks.58.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
713
+ "esmc.transformer.blocks.58.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
714
+ "esmc.transformer.blocks.58.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
715
+ "esmc.transformer.blocks.58.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
716
+ "esmc.transformer.blocks.58.attn.out_proj.weight": "model-00004-of-00006.safetensors",
717
+ "esmc.transformer.blocks.58.attn.q_ln.weight": "model-00004-of-00006.safetensors",
718
+ "esmc.transformer.blocks.58.ffn._extra_state": "model-00001-of-00006.safetensors",
719
+ "esmc.transformer.blocks.58.ffn.fc1_weight": "model-00004-of-00006.safetensors",
720
+ "esmc.transformer.blocks.58.ffn.fc2_weight": "model-00004-of-00006.safetensors",
721
+ "esmc.transformer.blocks.58.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
722
+ "esmc.transformer.blocks.58.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
723
+ "esmc.transformer.blocks.59.attn.k_ln.weight": "model-00004-of-00006.safetensors",
724
+ "esmc.transformer.blocks.59.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
725
+ "esmc.transformer.blocks.59.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
726
+ "esmc.transformer.blocks.59.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
727
+ "esmc.transformer.blocks.59.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
728
+ "esmc.transformer.blocks.59.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
729
+ "esmc.transformer.blocks.59.attn.out_proj.weight": "model-00004-of-00006.safetensors",
730
+ "esmc.transformer.blocks.59.attn.q_ln.weight": "model-00004-of-00006.safetensors",
731
+ "esmc.transformer.blocks.59.ffn._extra_state": "model-00001-of-00006.safetensors",
732
+ "esmc.transformer.blocks.59.ffn.fc1_weight": "model-00004-of-00006.safetensors",
733
+ "esmc.transformer.blocks.59.ffn.fc2_weight": "model-00004-of-00006.safetensors",
734
+ "esmc.transformer.blocks.59.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
735
+ "esmc.transformer.blocks.59.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
736
+ "esmc.transformer.blocks.6.attn.k_ln.weight": "model-00001-of-00006.safetensors",
737
+ "esmc.transformer.blocks.6.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
738
+ "esmc.transformer.blocks.6.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
739
+ "esmc.transformer.blocks.6.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
740
+ "esmc.transformer.blocks.6.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
741
+ "esmc.transformer.blocks.6.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
742
+ "esmc.transformer.blocks.6.attn.out_proj.weight": "model-00001-of-00006.safetensors",
743
+ "esmc.transformer.blocks.6.attn.q_ln.weight": "model-00001-of-00006.safetensors",
744
+ "esmc.transformer.blocks.6.ffn._extra_state": "model-00001-of-00006.safetensors",
745
+ "esmc.transformer.blocks.6.ffn.fc1_weight": "model-00001-of-00006.safetensors",
746
+ "esmc.transformer.blocks.6.ffn.fc2_weight": "model-00001-of-00006.safetensors",
747
+ "esmc.transformer.blocks.6.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
748
+ "esmc.transformer.blocks.6.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
749
+ "esmc.transformer.blocks.60.attn.k_ln.weight": "model-00004-of-00006.safetensors",
750
+ "esmc.transformer.blocks.60.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
751
+ "esmc.transformer.blocks.60.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
752
+ "esmc.transformer.blocks.60.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
753
+ "esmc.transformer.blocks.60.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
754
+ "esmc.transformer.blocks.60.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
755
+ "esmc.transformer.blocks.60.attn.out_proj.weight": "model-00004-of-00006.safetensors",
756
+ "esmc.transformer.blocks.60.attn.q_ln.weight": "model-00004-of-00006.safetensors",
757
+ "esmc.transformer.blocks.60.ffn._extra_state": "model-00001-of-00006.safetensors",
758
+ "esmc.transformer.blocks.60.ffn.fc1_weight": "model-00004-of-00006.safetensors",
759
+ "esmc.transformer.blocks.60.ffn.fc2_weight": "model-00004-of-00006.safetensors",
760
+ "esmc.transformer.blocks.60.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
761
+ "esmc.transformer.blocks.60.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
762
+ "esmc.transformer.blocks.61.attn.k_ln.weight": "model-00004-of-00006.safetensors",
763
+ "esmc.transformer.blocks.61.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
764
+ "esmc.transformer.blocks.61.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
765
+ "esmc.transformer.blocks.61.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
766
+ "esmc.transformer.blocks.61.attn.layernorm_qkv.weight": "model-00004-of-00006.safetensors",
767
+ "esmc.transformer.blocks.61.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
768
+ "esmc.transformer.blocks.61.attn.out_proj.weight": "model-00004-of-00006.safetensors",
769
+ "esmc.transformer.blocks.61.attn.q_ln.weight": "model-00004-of-00006.safetensors",
770
+ "esmc.transformer.blocks.61.ffn._extra_state": "model-00001-of-00006.safetensors",
771
+ "esmc.transformer.blocks.61.ffn.fc1_weight": "model-00004-of-00006.safetensors",
772
+ "esmc.transformer.blocks.61.ffn.fc2_weight": "model-00004-of-00006.safetensors",
773
+ "esmc.transformer.blocks.61.ffn.layer_norm_bias": "model-00004-of-00006.safetensors",
774
+ "esmc.transformer.blocks.61.ffn.layer_norm_weight": "model-00004-of-00006.safetensors",
775
+ "esmc.transformer.blocks.62.attn.k_ln.weight": "model-00005-of-00006.safetensors",
776
+ "esmc.transformer.blocks.62.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
777
+ "esmc.transformer.blocks.62.attn.layernorm_qkv.layer_norm_bias": "model-00004-of-00006.safetensors",
778
+ "esmc.transformer.blocks.62.attn.layernorm_qkv.layer_norm_weight": "model-00004-of-00006.safetensors",
779
+ "esmc.transformer.blocks.62.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
780
+ "esmc.transformer.blocks.62.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
781
+ "esmc.transformer.blocks.62.attn.out_proj.weight": "model-00005-of-00006.safetensors",
782
+ "esmc.transformer.blocks.62.attn.q_ln.weight": "model-00005-of-00006.safetensors",
783
+ "esmc.transformer.blocks.62.ffn._extra_state": "model-00001-of-00006.safetensors",
784
+ "esmc.transformer.blocks.62.ffn.fc1_weight": "model-00005-of-00006.safetensors",
785
+ "esmc.transformer.blocks.62.ffn.fc2_weight": "model-00005-of-00006.safetensors",
786
+ "esmc.transformer.blocks.62.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
787
+ "esmc.transformer.blocks.62.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
788
+ "esmc.transformer.blocks.63.attn.k_ln.weight": "model-00005-of-00006.safetensors",
789
+ "esmc.transformer.blocks.63.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
790
+ "esmc.transformer.blocks.63.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
791
+ "esmc.transformer.blocks.63.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
792
+ "esmc.transformer.blocks.63.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
793
+ "esmc.transformer.blocks.63.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
794
+ "esmc.transformer.blocks.63.attn.out_proj.weight": "model-00005-of-00006.safetensors",
795
+ "esmc.transformer.blocks.63.attn.q_ln.weight": "model-00005-of-00006.safetensors",
796
+ "esmc.transformer.blocks.63.ffn._extra_state": "model-00001-of-00006.safetensors",
797
+ "esmc.transformer.blocks.63.ffn.fc1_weight": "model-00005-of-00006.safetensors",
798
+ "esmc.transformer.blocks.63.ffn.fc2_weight": "model-00005-of-00006.safetensors",
799
+ "esmc.transformer.blocks.63.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
800
+ "esmc.transformer.blocks.63.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
801
+ "esmc.transformer.blocks.64.attn.k_ln.weight": "model-00005-of-00006.safetensors",
802
+ "esmc.transformer.blocks.64.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
803
+ "esmc.transformer.blocks.64.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
804
+ "esmc.transformer.blocks.64.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
805
+ "esmc.transformer.blocks.64.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
806
+ "esmc.transformer.blocks.64.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
807
+ "esmc.transformer.blocks.64.attn.out_proj.weight": "model-00005-of-00006.safetensors",
808
+ "esmc.transformer.blocks.64.attn.q_ln.weight": "model-00005-of-00006.safetensors",
809
+ "esmc.transformer.blocks.64.ffn._extra_state": "model-00001-of-00006.safetensors",
810
+ "esmc.transformer.blocks.64.ffn.fc1_weight": "model-00005-of-00006.safetensors",
811
+ "esmc.transformer.blocks.64.ffn.fc2_weight": "model-00005-of-00006.safetensors",
812
+ "esmc.transformer.blocks.64.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
813
+ "esmc.transformer.blocks.64.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
814
+ "esmc.transformer.blocks.65.attn.k_ln.weight": "model-00005-of-00006.safetensors",
815
+ "esmc.transformer.blocks.65.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
816
+ "esmc.transformer.blocks.65.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
817
+ "esmc.transformer.blocks.65.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
818
+ "esmc.transformer.blocks.65.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
819
+ "esmc.transformer.blocks.65.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
820
+ "esmc.transformer.blocks.65.attn.out_proj.weight": "model-00005-of-00006.safetensors",
821
+ "esmc.transformer.blocks.65.attn.q_ln.weight": "model-00005-of-00006.safetensors",
822
+ "esmc.transformer.blocks.65.ffn._extra_state": "model-00001-of-00006.safetensors",
823
+ "esmc.transformer.blocks.65.ffn.fc1_weight": "model-00005-of-00006.safetensors",
824
+ "esmc.transformer.blocks.65.ffn.fc2_weight": "model-00005-of-00006.safetensors",
825
+ "esmc.transformer.blocks.65.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
826
+ "esmc.transformer.blocks.65.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
827
+ "esmc.transformer.blocks.66.attn.k_ln.weight": "model-00005-of-00006.safetensors",
828
+ "esmc.transformer.blocks.66.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
829
+ "esmc.transformer.blocks.66.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
830
+ "esmc.transformer.blocks.66.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
831
+ "esmc.transformer.blocks.66.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
832
+ "esmc.transformer.blocks.66.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
833
+ "esmc.transformer.blocks.66.attn.out_proj.weight": "model-00005-of-00006.safetensors",
834
+ "esmc.transformer.blocks.66.attn.q_ln.weight": "model-00005-of-00006.safetensors",
835
+ "esmc.transformer.blocks.66.ffn._extra_state": "model-00001-of-00006.safetensors",
836
+ "esmc.transformer.blocks.66.ffn.fc1_weight": "model-00005-of-00006.safetensors",
837
+ "esmc.transformer.blocks.66.ffn.fc2_weight": "model-00005-of-00006.safetensors",
838
+ "esmc.transformer.blocks.66.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
839
+ "esmc.transformer.blocks.66.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
840
+ "esmc.transformer.blocks.67.attn.k_ln.weight": "model-00005-of-00006.safetensors",
841
+ "esmc.transformer.blocks.67.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
842
+ "esmc.transformer.blocks.67.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
843
+ "esmc.transformer.blocks.67.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
844
+ "esmc.transformer.blocks.67.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
845
+ "esmc.transformer.blocks.67.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
846
+ "esmc.transformer.blocks.67.attn.out_proj.weight": "model-00005-of-00006.safetensors",
847
+ "esmc.transformer.blocks.67.attn.q_ln.weight": "model-00005-of-00006.safetensors",
848
+ "esmc.transformer.blocks.67.ffn._extra_state": "model-00001-of-00006.safetensors",
849
+ "esmc.transformer.blocks.67.ffn.fc1_weight": "model-00005-of-00006.safetensors",
850
+ "esmc.transformer.blocks.67.ffn.fc2_weight": "model-00005-of-00006.safetensors",
851
+ "esmc.transformer.blocks.67.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
852
+ "esmc.transformer.blocks.67.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
853
+ "esmc.transformer.blocks.68.attn.k_ln.weight": "model-00005-of-00006.safetensors",
854
+ "esmc.transformer.blocks.68.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
855
+ "esmc.transformer.blocks.68.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
856
+ "esmc.transformer.blocks.68.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
857
+ "esmc.transformer.blocks.68.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
858
+ "esmc.transformer.blocks.68.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
859
+ "esmc.transformer.blocks.68.attn.out_proj.weight": "model-00005-of-00006.safetensors",
860
+ "esmc.transformer.blocks.68.attn.q_ln.weight": "model-00005-of-00006.safetensors",
861
+ "esmc.transformer.blocks.68.ffn._extra_state": "model-00001-of-00006.safetensors",
862
+ "esmc.transformer.blocks.68.ffn.fc1_weight": "model-00005-of-00006.safetensors",
863
+ "esmc.transformer.blocks.68.ffn.fc2_weight": "model-00005-of-00006.safetensors",
864
+ "esmc.transformer.blocks.68.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
865
+ "esmc.transformer.blocks.68.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
866
+ "esmc.transformer.blocks.69.attn.k_ln.weight": "model-00005-of-00006.safetensors",
867
+ "esmc.transformer.blocks.69.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
868
+ "esmc.transformer.blocks.69.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
869
+ "esmc.transformer.blocks.69.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
870
+ "esmc.transformer.blocks.69.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
871
+ "esmc.transformer.blocks.69.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
872
+ "esmc.transformer.blocks.69.attn.out_proj.weight": "model-00005-of-00006.safetensors",
873
+ "esmc.transformer.blocks.69.attn.q_ln.weight": "model-00005-of-00006.safetensors",
874
+ "esmc.transformer.blocks.69.ffn._extra_state": "model-00001-of-00006.safetensors",
875
+ "esmc.transformer.blocks.69.ffn.fc1_weight": "model-00005-of-00006.safetensors",
876
+ "esmc.transformer.blocks.69.ffn.fc2_weight": "model-00005-of-00006.safetensors",
877
+ "esmc.transformer.blocks.69.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
878
+ "esmc.transformer.blocks.69.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
879
+ "esmc.transformer.blocks.7.attn.k_ln.weight": "model-00001-of-00006.safetensors",
880
+ "esmc.transformer.blocks.7.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
881
+ "esmc.transformer.blocks.7.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
882
+ "esmc.transformer.blocks.7.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
883
+ "esmc.transformer.blocks.7.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
884
+ "esmc.transformer.blocks.7.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
885
+ "esmc.transformer.blocks.7.attn.out_proj.weight": "model-00001-of-00006.safetensors",
886
+ "esmc.transformer.blocks.7.attn.q_ln.weight": "model-00001-of-00006.safetensors",
887
+ "esmc.transformer.blocks.7.ffn._extra_state": "model-00001-of-00006.safetensors",
888
+ "esmc.transformer.blocks.7.ffn.fc1_weight": "model-00001-of-00006.safetensors",
889
+ "esmc.transformer.blocks.7.ffn.fc2_weight": "model-00001-of-00006.safetensors",
890
+ "esmc.transformer.blocks.7.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
891
+ "esmc.transformer.blocks.7.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
892
+ "esmc.transformer.blocks.70.attn.k_ln.weight": "model-00005-of-00006.safetensors",
893
+ "esmc.transformer.blocks.70.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
894
+ "esmc.transformer.blocks.70.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
895
+ "esmc.transformer.blocks.70.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
896
+ "esmc.transformer.blocks.70.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
897
+ "esmc.transformer.blocks.70.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
898
+ "esmc.transformer.blocks.70.attn.out_proj.weight": "model-00005-of-00006.safetensors",
899
+ "esmc.transformer.blocks.70.attn.q_ln.weight": "model-00005-of-00006.safetensors",
900
+ "esmc.transformer.blocks.70.ffn._extra_state": "model-00001-of-00006.safetensors",
901
+ "esmc.transformer.blocks.70.ffn.fc1_weight": "model-00005-of-00006.safetensors",
902
+ "esmc.transformer.blocks.70.ffn.fc2_weight": "model-00005-of-00006.safetensors",
903
+ "esmc.transformer.blocks.70.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
904
+ "esmc.transformer.blocks.70.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
905
+ "esmc.transformer.blocks.71.attn.k_ln.weight": "model-00005-of-00006.safetensors",
906
+ "esmc.transformer.blocks.71.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
907
+ "esmc.transformer.blocks.71.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
908
+ "esmc.transformer.blocks.71.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
909
+ "esmc.transformer.blocks.71.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
910
+ "esmc.transformer.blocks.71.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
911
+ "esmc.transformer.blocks.71.attn.out_proj.weight": "model-00005-of-00006.safetensors",
912
+ "esmc.transformer.blocks.71.attn.q_ln.weight": "model-00005-of-00006.safetensors",
913
+ "esmc.transformer.blocks.71.ffn._extra_state": "model-00001-of-00006.safetensors",
914
+ "esmc.transformer.blocks.71.ffn.fc1_weight": "model-00005-of-00006.safetensors",
915
+ "esmc.transformer.blocks.71.ffn.fc2_weight": "model-00005-of-00006.safetensors",
916
+ "esmc.transformer.blocks.71.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
917
+ "esmc.transformer.blocks.71.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
918
+ "esmc.transformer.blocks.72.attn.k_ln.weight": "model-00005-of-00006.safetensors",
919
+ "esmc.transformer.blocks.72.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
920
+ "esmc.transformer.blocks.72.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
921
+ "esmc.transformer.blocks.72.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
922
+ "esmc.transformer.blocks.72.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
923
+ "esmc.transformer.blocks.72.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
924
+ "esmc.transformer.blocks.72.attn.out_proj.weight": "model-00005-of-00006.safetensors",
925
+ "esmc.transformer.blocks.72.attn.q_ln.weight": "model-00005-of-00006.safetensors",
926
+ "esmc.transformer.blocks.72.ffn._extra_state": "model-00001-of-00006.safetensors",
927
+ "esmc.transformer.blocks.72.ffn.fc1_weight": "model-00005-of-00006.safetensors",
928
+ "esmc.transformer.blocks.72.ffn.fc2_weight": "model-00005-of-00006.safetensors",
929
+ "esmc.transformer.blocks.72.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
930
+ "esmc.transformer.blocks.72.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
931
+ "esmc.transformer.blocks.73.attn.k_ln.weight": "model-00005-of-00006.safetensors",
932
+ "esmc.transformer.blocks.73.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
933
+ "esmc.transformer.blocks.73.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
934
+ "esmc.transformer.blocks.73.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
935
+ "esmc.transformer.blocks.73.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
936
+ "esmc.transformer.blocks.73.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
937
+ "esmc.transformer.blocks.73.attn.out_proj.weight": "model-00005-of-00006.safetensors",
938
+ "esmc.transformer.blocks.73.attn.q_ln.weight": "model-00005-of-00006.safetensors",
939
+ "esmc.transformer.blocks.73.ffn._extra_state": "model-00001-of-00006.safetensors",
940
+ "esmc.transformer.blocks.73.ffn.fc1_weight": "model-00005-of-00006.safetensors",
941
+ "esmc.transformer.blocks.73.ffn.fc2_weight": "model-00005-of-00006.safetensors",
942
+ "esmc.transformer.blocks.73.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
943
+ "esmc.transformer.blocks.73.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
944
+ "esmc.transformer.blocks.74.attn.k_ln.weight": "model-00005-of-00006.safetensors",
945
+ "esmc.transformer.blocks.74.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
946
+ "esmc.transformer.blocks.74.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
947
+ "esmc.transformer.blocks.74.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
948
+ "esmc.transformer.blocks.74.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
949
+ "esmc.transformer.blocks.74.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
950
+ "esmc.transformer.blocks.74.attn.out_proj.weight": "model-00005-of-00006.safetensors",
951
+ "esmc.transformer.blocks.74.attn.q_ln.weight": "model-00005-of-00006.safetensors",
952
+ "esmc.transformer.blocks.74.ffn._extra_state": "model-00001-of-00006.safetensors",
953
+ "esmc.transformer.blocks.74.ffn.fc1_weight": "model-00005-of-00006.safetensors",
954
+ "esmc.transformer.blocks.74.ffn.fc2_weight": "model-00005-of-00006.safetensors",
955
+ "esmc.transformer.blocks.74.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
956
+ "esmc.transformer.blocks.74.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
957
+ "esmc.transformer.blocks.75.attn.k_ln.weight": "model-00005-of-00006.safetensors",
958
+ "esmc.transformer.blocks.75.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
959
+ "esmc.transformer.blocks.75.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
960
+ "esmc.transformer.blocks.75.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
961
+ "esmc.transformer.blocks.75.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
962
+ "esmc.transformer.blocks.75.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
963
+ "esmc.transformer.blocks.75.attn.out_proj.weight": "model-00005-of-00006.safetensors",
964
+ "esmc.transformer.blocks.75.attn.q_ln.weight": "model-00005-of-00006.safetensors",
965
+ "esmc.transformer.blocks.75.ffn._extra_state": "model-00001-of-00006.safetensors",
966
+ "esmc.transformer.blocks.75.ffn.fc1_weight": "model-00005-of-00006.safetensors",
967
+ "esmc.transformer.blocks.75.ffn.fc2_weight": "model-00005-of-00006.safetensors",
968
+ "esmc.transformer.blocks.75.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
969
+ "esmc.transformer.blocks.75.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
970
+ "esmc.transformer.blocks.76.attn.k_ln.weight": "model-00005-of-00006.safetensors",
971
+ "esmc.transformer.blocks.76.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
972
+ "esmc.transformer.blocks.76.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
973
+ "esmc.transformer.blocks.76.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
974
+ "esmc.transformer.blocks.76.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
975
+ "esmc.transformer.blocks.76.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
976
+ "esmc.transformer.blocks.76.attn.out_proj.weight": "model-00005-of-00006.safetensors",
977
+ "esmc.transformer.blocks.76.attn.q_ln.weight": "model-00005-of-00006.safetensors",
978
+ "esmc.transformer.blocks.76.ffn._extra_state": "model-00001-of-00006.safetensors",
979
+ "esmc.transformer.blocks.76.ffn.fc1_weight": "model-00005-of-00006.safetensors",
980
+ "esmc.transformer.blocks.76.ffn.fc2_weight": "model-00005-of-00006.safetensors",
981
+ "esmc.transformer.blocks.76.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
982
+ "esmc.transformer.blocks.76.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
983
+ "esmc.transformer.blocks.77.attn.k_ln.weight": "model-00005-of-00006.safetensors",
984
+ "esmc.transformer.blocks.77.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
985
+ "esmc.transformer.blocks.77.attn.layernorm_qkv.layer_norm_bias": "model-00005-of-00006.safetensors",
986
+ "esmc.transformer.blocks.77.attn.layernorm_qkv.layer_norm_weight": "model-00005-of-00006.safetensors",
987
+ "esmc.transformer.blocks.77.attn.layernorm_qkv.weight": "model-00005-of-00006.safetensors",
988
+ "esmc.transformer.blocks.77.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
989
+ "esmc.transformer.blocks.77.attn.out_proj.weight": "model-00005-of-00006.safetensors",
990
+ "esmc.transformer.blocks.77.attn.q_ln.weight": "model-00005-of-00006.safetensors",
991
+ "esmc.transformer.blocks.77.ffn._extra_state": "model-00001-of-00006.safetensors",
992
+ "esmc.transformer.blocks.77.ffn.fc1_weight": "model-00006-of-00006.safetensors",
993
+ "esmc.transformer.blocks.77.ffn.fc2_weight": "model-00006-of-00006.safetensors",
994
+ "esmc.transformer.blocks.77.ffn.layer_norm_bias": "model-00005-of-00006.safetensors",
995
+ "esmc.transformer.blocks.77.ffn.layer_norm_weight": "model-00005-of-00006.safetensors",
996
+ "esmc.transformer.blocks.78.attn.k_ln.weight": "model-00006-of-00006.safetensors",
997
+ "esmc.transformer.blocks.78.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
998
+ "esmc.transformer.blocks.78.attn.layernorm_qkv.layer_norm_bias": "model-00006-of-00006.safetensors",
999
+ "esmc.transformer.blocks.78.attn.layernorm_qkv.layer_norm_weight": "model-00006-of-00006.safetensors",
1000
+ "esmc.transformer.blocks.78.attn.layernorm_qkv.weight": "model-00006-of-00006.safetensors",
1001
+ "esmc.transformer.blocks.78.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
1002
+ "esmc.transformer.blocks.78.attn.out_proj.weight": "model-00006-of-00006.safetensors",
1003
+ "esmc.transformer.blocks.78.attn.q_ln.weight": "model-00006-of-00006.safetensors",
1004
+ "esmc.transformer.blocks.78.ffn._extra_state": "model-00001-of-00006.safetensors",
1005
+ "esmc.transformer.blocks.78.ffn.fc1_weight": "model-00006-of-00006.safetensors",
1006
+ "esmc.transformer.blocks.78.ffn.fc2_weight": "model-00006-of-00006.safetensors",
1007
+ "esmc.transformer.blocks.78.ffn.layer_norm_bias": "model-00006-of-00006.safetensors",
1008
+ "esmc.transformer.blocks.78.ffn.layer_norm_weight": "model-00006-of-00006.safetensors",
1009
+ "esmc.transformer.blocks.79.attn.k_ln.weight": "model-00006-of-00006.safetensors",
1010
+ "esmc.transformer.blocks.79.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
1011
+ "esmc.transformer.blocks.79.attn.layernorm_qkv.layer_norm_bias": "model-00006-of-00006.safetensors",
1012
+ "esmc.transformer.blocks.79.attn.layernorm_qkv.layer_norm_weight": "model-00006-of-00006.safetensors",
1013
+ "esmc.transformer.blocks.79.attn.layernorm_qkv.weight": "model-00006-of-00006.safetensors",
1014
+ "esmc.transformer.blocks.79.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
1015
+ "esmc.transformer.blocks.79.attn.out_proj.weight": "model-00006-of-00006.safetensors",
1016
+ "esmc.transformer.blocks.79.attn.q_ln.weight": "model-00006-of-00006.safetensors",
1017
+ "esmc.transformer.blocks.79.ffn._extra_state": "model-00001-of-00006.safetensors",
1018
+ "esmc.transformer.blocks.79.ffn.fc1_weight": "model-00006-of-00006.safetensors",
1019
+ "esmc.transformer.blocks.79.ffn.fc2_weight": "model-00006-of-00006.safetensors",
1020
+ "esmc.transformer.blocks.79.ffn.layer_norm_bias": "model-00006-of-00006.safetensors",
1021
+ "esmc.transformer.blocks.79.ffn.layer_norm_weight": "model-00006-of-00006.safetensors",
1022
+ "esmc.transformer.blocks.8.attn.k_ln.weight": "model-00001-of-00006.safetensors",
1023
+ "esmc.transformer.blocks.8.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
1024
+ "esmc.transformer.blocks.8.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
1025
+ "esmc.transformer.blocks.8.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
1026
+ "esmc.transformer.blocks.8.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
1027
+ "esmc.transformer.blocks.8.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
1028
+ "esmc.transformer.blocks.8.attn.out_proj.weight": "model-00001-of-00006.safetensors",
1029
+ "esmc.transformer.blocks.8.attn.q_ln.weight": "model-00001-of-00006.safetensors",
1030
+ "esmc.transformer.blocks.8.ffn._extra_state": "model-00001-of-00006.safetensors",
1031
+ "esmc.transformer.blocks.8.ffn.fc1_weight": "model-00001-of-00006.safetensors",
1032
+ "esmc.transformer.blocks.8.ffn.fc2_weight": "model-00001-of-00006.safetensors",
1033
+ "esmc.transformer.blocks.8.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
1034
+ "esmc.transformer.blocks.8.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
1035
+ "esmc.transformer.blocks.9.attn.k_ln.weight": "model-00001-of-00006.safetensors",
1036
+ "esmc.transformer.blocks.9.attn.layernorm_qkv._extra_state": "model-00001-of-00006.safetensors",
1037
+ "esmc.transformer.blocks.9.attn.layernorm_qkv.layer_norm_bias": "model-00001-of-00006.safetensors",
1038
+ "esmc.transformer.blocks.9.attn.layernorm_qkv.layer_norm_weight": "model-00001-of-00006.safetensors",
1039
+ "esmc.transformer.blocks.9.attn.layernorm_qkv.weight": "model-00001-of-00006.safetensors",
1040
+ "esmc.transformer.blocks.9.attn.out_proj._extra_state": "model-00001-of-00006.safetensors",
1041
+ "esmc.transformer.blocks.9.attn.out_proj.weight": "model-00001-of-00006.safetensors",
1042
+ "esmc.transformer.blocks.9.attn.q_ln.weight": "model-00001-of-00006.safetensors",
1043
+ "esmc.transformer.blocks.9.ffn._extra_state": "model-00001-of-00006.safetensors",
1044
+ "esmc.transformer.blocks.9.ffn.fc1_weight": "model-00001-of-00006.safetensors",
1045
+ "esmc.transformer.blocks.9.ffn.fc2_weight": "model-00001-of-00006.safetensors",
1046
+ "esmc.transformer.blocks.9.ffn.layer_norm_bias": "model-00001-of-00006.safetensors",
1047
+ "esmc.transformer.blocks.9.ffn.layer_norm_weight": "model-00001-of-00006.safetensors",
1048
+ "esmc.transformer.norm.weight": "model-00006-of-00006.safetensors",
1049
+ "lm_head.0.bias": "model-00006-of-00006.safetensors",
1050
+ "lm_head.0.weight": "model-00006-of-00006.safetensors",
1051
+ "lm_head.2.bias": "model-00006-of-00006.safetensors",
1052
+ "lm_head.2.weight": "model-00006-of-00006.safetensors",
1053
+ "lm_head.3.bias": "model-00006-of-00006.safetensors",
1054
+ "lm_head.3.weight": "model-00006-of-00006.safetensors"
1055
+ }
1056
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "|"
4
+ ],
5
+ "cls_token": "<cls>",
6
+ "eos_token": "<eos>",
7
+ "mask_token": "<mask>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<unk>"
10
+ }
tokenizer.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<cls>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<eos>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 31,
44
+ "content": "|",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 32,
53
+ "content": "<mask>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ }
60
+ ],
61
+ "normalizer": null,
62
+ "pre_tokenizer": null,
63
+ "post_processor": {
64
+ "type": "TemplateProcessing",
65
+ "single": [
66
+ {
67
+ "SpecialToken": {
68
+ "id": "<cls>",
69
+ "type_id": 0
70
+ }
71
+ },
72
+ {
73
+ "Sequence": {
74
+ "id": "A",
75
+ "type_id": 0
76
+ }
77
+ },
78
+ {
79
+ "SpecialToken": {
80
+ "id": "<eos>",
81
+ "type_id": 0
82
+ }
83
+ }
84
+ ],
85
+ "pair": [
86
+ {
87
+ "Sequence": {
88
+ "id": "A",
89
+ "type_id": 0
90
+ }
91
+ },
92
+ {
93
+ "Sequence": {
94
+ "id": "B",
95
+ "type_id": 1
96
+ }
97
+ }
98
+ ],
99
+ "special_tokens": {
100
+ "<cls>": {
101
+ "id": "<cls>",
102
+ "ids": [
103
+ 0
104
+ ],
105
+ "tokens": [
106
+ "<cls>"
107
+ ]
108
+ },
109
+ "<eos>": {
110
+ "id": "<eos>",
111
+ "ids": [
112
+ 2
113
+ ],
114
+ "tokens": [
115
+ "<eos>"
116
+ ]
117
+ }
118
+ }
119
+ },
120
+ "decoder": null,
121
+ "model": {
122
+ "type": "BPE",
123
+ "dropout": null,
124
+ "unk_token": "<unk>",
125
+ "continuing_subword_prefix": null,
126
+ "end_of_word_suffix": null,
127
+ "fuse_unk": false,
128
+ "byte_fallback": false,
129
+ "ignore_merges": false,
130
+ "vocab": {
131
+ "<cls>": 0,
132
+ "<pad>": 1,
133
+ "<eos>": 2,
134
+ "<unk>": 3,
135
+ "L": 4,
136
+ "A": 5,
137
+ "G": 6,
138
+ "V": 7,
139
+ "S": 8,
140
+ "E": 9,
141
+ "R": 10,
142
+ "T": 11,
143
+ "I": 12,
144
+ "D": 13,
145
+ "P": 14,
146
+ "K": 15,
147
+ "Q": 16,
148
+ "N": 17,
149
+ "F": 18,
150
+ "Y": 19,
151
+ "M": 20,
152
+ "H": 21,
153
+ "W": 22,
154
+ "C": 23,
155
+ "X": 24,
156
+ "B": 25,
157
+ "U": 26,
158
+ "Z": 27,
159
+ "O": 28,
160
+ ".": 29,
161
+ "-": 30,
162
+ "|": 31,
163
+ "<mask>": 32
164
+ },
165
+ "merges": []
166
+ }
167
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "31": {
36
+ "content": "|",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32": {
44
+ "content": "<mask>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "additional_special_tokens": [
53
+ "|"
54
+ ],
55
+ "bos_token": "<cls>",
56
+ "clean_up_tokenization_spaces": false,
57
+ "cls_token": "<cls>",
58
+ "eos_token": "<eos>",
59
+ "extra_special_tokens": {},
60
+ "mask_token": "<mask>",
61
+ "model_max_length": 1000000000000000019884624838656,
62
+ "pad_token": "<pad>",
63
+ "tokenizer_class": "ESMCTokenizer",
64
+ "unk_token": "<unk>"
65
+ }