shanearora commited on
Commit
79502ad
1 Parent(s): 21c57a8

Upload OLMoForCausalLM

Browse files
config.json CHANGED
@@ -1,55 +1,28 @@
1
  {
2
- "_name_or_path": "allenai/OLMo-7B-Twin-2T",
3
- "activation_type": "swiglu",
4
- "alibi": false,
5
- "alibi_bias_max": 8.0,
6
  "architectures": [
7
  "OLMoForCausalLM"
8
  ],
 
9
  "attention_dropout": 0.0,
10
- "attention_layer_norm": false,
11
- "attention_layer_norm_with_affine": false,
12
- "auto_map": {
13
- "AutoConfig": "allenai/OLMo-7B-Twin-2T--configuration_olmo.OLMoConfig",
14
- "AutoModelForCausalLM": "allenai/OLMo-7B-Twin-2T--modeling_olmo.OLMoForCausalLM",
15
- "AutoTokenizer": [
16
- "allenai/OLMo-7B-Twin-2T--tokenization_olmo_fast.OLMoTokenizerFast",
17
- "allenai/OLMo-7B-Twin-2T--tokenization_olmo_fast.OLMoTokenizerFast"
18
- ]
19
- },
20
- "bias_for_layer_norm": false,
21
- "block_group_size": 1,
22
- "block_type": "sequential",
23
  "clip_qkv": null,
24
- "d_model": 4096,
25
- "embedding_dropout": 0.0,
26
- "embedding_size": 50304,
27
- "eos_token_id": 50279,
28
- "flash_attention": false,
29
- "include_bias": false,
30
- "init_cutoff_factor": null,
31
- "init_device": "meta",
32
- "init_fn": "mitchell",
33
- "init_std": 0.02,
34
- "layer_norm_type": "default",
35
- "layer_norm_with_affine": false,
36
- "max_sequence_length": 2048,
37
- "mlp_hidden_size": 22016,
38
- "mlp_ratio": 4,
39
  "model_type": "olmo",
40
- "multi_query_attention": false,
41
- "n_heads": 32,
42
- "n_kv_heads": null,
43
- "n_layers": 32,
44
  "pad_token_id": 1,
45
- "precision": "amp_bf16",
46
- "residual_dropout": 0.0,
47
- "rope": true,
48
- "rope_full_precision": true,
49
- "scale_logits": false,
50
  "torch_dtype": "float32",
51
- "transformers_version": "4.39.3",
52
  "use_cache": true,
53
- "vocab_size": 50280,
54
- "weight_tying": false
55
  }
 
1
  {
2
+ "_name_or_path": "/home/ubuntu/checkpoints/olmo-7b-twin-2t-6",
 
 
 
3
  "architectures": [
4
  "OLMoForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "clip_qkv": null,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 2048,
 
 
 
 
 
 
 
 
 
15
  "model_type": "olmo",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
 
19
  "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
 
24
  "torch_dtype": "float32",
25
+ "transformers_version": "4.40.0.dev0",
26
  "use_cache": true,
27
+ "vocab_size": 50304
 
28
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "eos_token_id": 50279,
4
  "pad_token_id": 1,
5
- "transformers_version": "4.39.3"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "eos_token_id": 0,
4
  "pad_token_id": 1,
5
+ "transformers_version": "4.40.0.dev0"
6
  }
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38896a77697663bf47eb8cc031ec9cf731ab66f5f62fe4d555bae2fefedeaf8c
3
- size 4938795616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d00fb4395021dd0d1c318a9201074097e01a79b121bbaf8391822fcf4aa46ee
3
+ size 4938797232
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a7e402b3c73b34699a19f5514b4b01db5b497e7f5e5206fc88fdcb66d5468b
3
- size 4857006944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1d063a2ce011d7ec77bba7d5fb2fa6578e972ae24538c44aa37378fd4c33f9
3
+ size 4991226840
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b654c915fa8ad84d4405fbfe2472d9b2b80f73af9009338942508de1ba7493c
3
- size 4857006960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0bb5590f8cf4f2bb5c092d32acdf5e40105bda505f982ef6499e8b657586b6
3
+ size 4924117904
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2754680e6f6f24a3cf0dbbc191f5e62e987af814cbf99aec595f8d6bbf27cd20
3
- size 4857006960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e5c05b505d6b9c42409fa2fcb2f1b77aeced2cae132eb7ccbac43f07a27f32
3
+ size 4857008920
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:950f1f5989192a94d4b7f136f2ce5270ad6bc3e819f9c94d3d7bb140262ac62a
3
- size 4857006960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e713e3f51f419c034d73c4edaeb4f871f7f78020ac9b1edcfcf3dde42c00300f
3
+ size 4857008920
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30fe3e45fbbc699da814d3632e9a53ebcb047bfce0dc8db3eb7de20373542bde
3
- size 3185575352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daea4e8fc43e5bbdeaafdef987a633b521c7a4015f59e2ae31937e7a5f901165
3
+ size 2984249384
model.safetensors.index.json CHANGED
@@ -3,135 +3,231 @@
3
  "total_size": 27552382976
4
  },
5
  "weight_map": {
6
- "model.transformer.blocks.0.att_proj.weight": "model-00001-of-00006.safetensors",
7
- "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00006.safetensors",
8
- "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00006.safetensors",
9
- "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00006.safetensors",
10
- "model.transformer.blocks.1.att_proj.weight": "model-00001-of-00006.safetensors",
11
- "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00006.safetensors",
12
- "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00006.safetensors",
13
- "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00006.safetensors",
14
- "model.transformer.blocks.10.att_proj.weight": "model-00002-of-00006.safetensors",
15
- "model.transformer.blocks.10.attn_out.weight": "model-00002-of-00006.safetensors",
16
- "model.transformer.blocks.10.ff_out.weight": "model-00002-of-00006.safetensors",
17
- "model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00006.safetensors",
18
- "model.transformer.blocks.11.att_proj.weight": "model-00003-of-00006.safetensors",
19
- "model.transformer.blocks.11.attn_out.weight": "model-00002-of-00006.safetensors",
20
- "model.transformer.blocks.11.ff_out.weight": "model-00003-of-00006.safetensors",
21
- "model.transformer.blocks.11.ff_proj.weight": "model-00003-of-00006.safetensors",
22
- "model.transformer.blocks.12.att_proj.weight": "model-00003-of-00006.safetensors",
23
- "model.transformer.blocks.12.attn_out.weight": "model-00003-of-00006.safetensors",
24
- "model.transformer.blocks.12.ff_out.weight": "model-00003-of-00006.safetensors",
25
- "model.transformer.blocks.12.ff_proj.weight": "model-00003-of-00006.safetensors",
26
- "model.transformer.blocks.13.att_proj.weight": "model-00003-of-00006.safetensors",
27
- "model.transformer.blocks.13.attn_out.weight": "model-00003-of-00006.safetensors",
28
- "model.transformer.blocks.13.ff_out.weight": "model-00003-of-00006.safetensors",
29
- "model.transformer.blocks.13.ff_proj.weight": "model-00003-of-00006.safetensors",
30
- "model.transformer.blocks.14.att_proj.weight": "model-00003-of-00006.safetensors",
31
- "model.transformer.blocks.14.attn_out.weight": "model-00003-of-00006.safetensors",
32
- "model.transformer.blocks.14.ff_out.weight": "model-00003-of-00006.safetensors",
33
- "model.transformer.blocks.14.ff_proj.weight": "model-00003-of-00006.safetensors",
34
- "model.transformer.blocks.15.att_proj.weight": "model-00003-of-00006.safetensors",
35
- "model.transformer.blocks.15.attn_out.weight": "model-00003-of-00006.safetensors",
36
- "model.transformer.blocks.15.ff_out.weight": "model-00003-of-00006.safetensors",
37
- "model.transformer.blocks.15.ff_proj.weight": "model-00003-of-00006.safetensors",
38
- "model.transformer.blocks.16.att_proj.weight": "model-00003-of-00006.safetensors",
39
- "model.transformer.blocks.16.attn_out.weight": "model-00003-of-00006.safetensors",
40
- "model.transformer.blocks.16.ff_out.weight": "model-00003-of-00006.safetensors",
41
- "model.transformer.blocks.16.ff_proj.weight": "model-00003-of-00006.safetensors",
42
- "model.transformer.blocks.17.att_proj.weight": "model-00004-of-00006.safetensors",
43
- "model.transformer.blocks.17.attn_out.weight": "model-00003-of-00006.safetensors",
44
- "model.transformer.blocks.17.ff_out.weight": "model-00004-of-00006.safetensors",
45
- "model.transformer.blocks.17.ff_proj.weight": "model-00004-of-00006.safetensors",
46
- "model.transformer.blocks.18.att_proj.weight": "model-00004-of-00006.safetensors",
47
- "model.transformer.blocks.18.attn_out.weight": "model-00004-of-00006.safetensors",
48
- "model.transformer.blocks.18.ff_out.weight": "model-00004-of-00006.safetensors",
49
- "model.transformer.blocks.18.ff_proj.weight": "model-00004-of-00006.safetensors",
50
- "model.transformer.blocks.19.att_proj.weight": "model-00004-of-00006.safetensors",
51
- "model.transformer.blocks.19.attn_out.weight": "model-00004-of-00006.safetensors",
52
- "model.transformer.blocks.19.ff_out.weight": "model-00004-of-00006.safetensors",
53
- "model.transformer.blocks.19.ff_proj.weight": "model-00004-of-00006.safetensors",
54
- "model.transformer.blocks.2.att_proj.weight": "model-00001-of-00006.safetensors",
55
- "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00006.safetensors",
56
- "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00006.safetensors",
57
- "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00006.safetensors",
58
- "model.transformer.blocks.20.att_proj.weight": "model-00004-of-00006.safetensors",
59
- "model.transformer.blocks.20.attn_out.weight": "model-00004-of-00006.safetensors",
60
- "model.transformer.blocks.20.ff_out.weight": "model-00004-of-00006.safetensors",
61
- "model.transformer.blocks.20.ff_proj.weight": "model-00004-of-00006.safetensors",
62
- "model.transformer.blocks.21.att_proj.weight": "model-00004-of-00006.safetensors",
63
- "model.transformer.blocks.21.attn_out.weight": "model-00004-of-00006.safetensors",
64
- "model.transformer.blocks.21.ff_out.weight": "model-00004-of-00006.safetensors",
65
- "model.transformer.blocks.21.ff_proj.weight": "model-00004-of-00006.safetensors",
66
- "model.transformer.blocks.22.att_proj.weight": "model-00004-of-00006.safetensors",
67
- "model.transformer.blocks.22.attn_out.weight": "model-00004-of-00006.safetensors",
68
- "model.transformer.blocks.22.ff_out.weight": "model-00004-of-00006.safetensors",
69
- "model.transformer.blocks.22.ff_proj.weight": "model-00004-of-00006.safetensors",
70
- "model.transformer.blocks.23.att_proj.weight": "model-00005-of-00006.safetensors",
71
- "model.transformer.blocks.23.attn_out.weight": "model-00004-of-00006.safetensors",
72
- "model.transformer.blocks.23.ff_out.weight": "model-00005-of-00006.safetensors",
73
- "model.transformer.blocks.23.ff_proj.weight": "model-00005-of-00006.safetensors",
74
- "model.transformer.blocks.24.att_proj.weight": "model-00005-of-00006.safetensors",
75
- "model.transformer.blocks.24.attn_out.weight": "model-00005-of-00006.safetensors",
76
- "model.transformer.blocks.24.ff_out.weight": "model-00005-of-00006.safetensors",
77
- "model.transformer.blocks.24.ff_proj.weight": "model-00005-of-00006.safetensors",
78
- "model.transformer.blocks.25.att_proj.weight": "model-00005-of-00006.safetensors",
79
- "model.transformer.blocks.25.attn_out.weight": "model-00005-of-00006.safetensors",
80
- "model.transformer.blocks.25.ff_out.weight": "model-00005-of-00006.safetensors",
81
- "model.transformer.blocks.25.ff_proj.weight": "model-00005-of-00006.safetensors",
82
- "model.transformer.blocks.26.att_proj.weight": "model-00005-of-00006.safetensors",
83
- "model.transformer.blocks.26.attn_out.weight": "model-00005-of-00006.safetensors",
84
- "model.transformer.blocks.26.ff_out.weight": "model-00005-of-00006.safetensors",
85
- "model.transformer.blocks.26.ff_proj.weight": "model-00005-of-00006.safetensors",
86
- "model.transformer.blocks.27.att_proj.weight": "model-00005-of-00006.safetensors",
87
- "model.transformer.blocks.27.attn_out.weight": "model-00005-of-00006.safetensors",
88
- "model.transformer.blocks.27.ff_out.weight": "model-00005-of-00006.safetensors",
89
- "model.transformer.blocks.27.ff_proj.weight": "model-00005-of-00006.safetensors",
90
- "model.transformer.blocks.28.att_proj.weight": "model-00005-of-00006.safetensors",
91
- "model.transformer.blocks.28.attn_out.weight": "model-00005-of-00006.safetensors",
92
- "model.transformer.blocks.28.ff_out.weight": "model-00005-of-00006.safetensors",
93
- "model.transformer.blocks.28.ff_proj.weight": "model-00005-of-00006.safetensors",
94
- "model.transformer.blocks.29.att_proj.weight": "model-00006-of-00006.safetensors",
95
- "model.transformer.blocks.29.attn_out.weight": "model-00005-of-00006.safetensors",
96
- "model.transformer.blocks.29.ff_out.weight": "model-00006-of-00006.safetensors",
97
- "model.transformer.blocks.29.ff_proj.weight": "model-00006-of-00006.safetensors",
98
- "model.transformer.blocks.3.att_proj.weight": "model-00001-of-00006.safetensors",
99
- "model.transformer.blocks.3.attn_out.weight": "model-00001-of-00006.safetensors",
100
- "model.transformer.blocks.3.ff_out.weight": "model-00001-of-00006.safetensors",
101
- "model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00006.safetensors",
102
- "model.transformer.blocks.30.att_proj.weight": "model-00006-of-00006.safetensors",
103
- "model.transformer.blocks.30.attn_out.weight": "model-00006-of-00006.safetensors",
104
- "model.transformer.blocks.30.ff_out.weight": "model-00006-of-00006.safetensors",
105
- "model.transformer.blocks.30.ff_proj.weight": "model-00006-of-00006.safetensors",
106
- "model.transformer.blocks.31.att_proj.weight": "model-00006-of-00006.safetensors",
107
- "model.transformer.blocks.31.attn_out.weight": "model-00006-of-00006.safetensors",
108
- "model.transformer.blocks.31.ff_out.weight": "model-00006-of-00006.safetensors",
109
- "model.transformer.blocks.31.ff_proj.weight": "model-00006-of-00006.safetensors",
110
- "model.transformer.blocks.4.att_proj.weight": "model-00001-of-00006.safetensors",
111
- "model.transformer.blocks.4.attn_out.weight": "model-00001-of-00006.safetensors",
112
- "model.transformer.blocks.4.ff_out.weight": "model-00001-of-00006.safetensors",
113
- "model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00006.safetensors",
114
- "model.transformer.blocks.5.att_proj.weight": "model-00002-of-00006.safetensors",
115
- "model.transformer.blocks.5.attn_out.weight": "model-00001-of-00006.safetensors",
116
- "model.transformer.blocks.5.ff_out.weight": "model-00002-of-00006.safetensors",
117
- "model.transformer.blocks.5.ff_proj.weight": "model-00002-of-00006.safetensors",
118
- "model.transformer.blocks.6.att_proj.weight": "model-00002-of-00006.safetensors",
119
- "model.transformer.blocks.6.attn_out.weight": "model-00002-of-00006.safetensors",
120
- "model.transformer.blocks.6.ff_out.weight": "model-00002-of-00006.safetensors",
121
- "model.transformer.blocks.6.ff_proj.weight": "model-00002-of-00006.safetensors",
122
- "model.transformer.blocks.7.att_proj.weight": "model-00002-of-00006.safetensors",
123
- "model.transformer.blocks.7.attn_out.weight": "model-00002-of-00006.safetensors",
124
- "model.transformer.blocks.7.ff_out.weight": "model-00002-of-00006.safetensors",
125
- "model.transformer.blocks.7.ff_proj.weight": "model-00002-of-00006.safetensors",
126
- "model.transformer.blocks.8.att_proj.weight": "model-00002-of-00006.safetensors",
127
- "model.transformer.blocks.8.attn_out.weight": "model-00002-of-00006.safetensors",
128
- "model.transformer.blocks.8.ff_out.weight": "model-00002-of-00006.safetensors",
129
- "model.transformer.blocks.8.ff_proj.weight": "model-00002-of-00006.safetensors",
130
- "model.transformer.blocks.9.att_proj.weight": "model-00002-of-00006.safetensors",
131
- "model.transformer.blocks.9.attn_out.weight": "model-00002-of-00006.safetensors",
132
- "model.transformer.blocks.9.ff_out.weight": "model-00002-of-00006.safetensors",
133
- "model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00006.safetensors",
134
- "model.transformer.ff_out.weight": "model-00006-of-00006.safetensors",
135
- "model.transformer.wte.weight": "model-00001-of-00006.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  }
 
3
  "total_size": 27552382976
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
23
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
24
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
25
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
30
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
31
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
32
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
34
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
44
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
72
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
73
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
74
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
79
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
80
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
82
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
83
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
85
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
86
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
87
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
88
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
89
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
93
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
94
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
95
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
96
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
97
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
98
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
99
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
121
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
122
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
123
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
128
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
129
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
130
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
131
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
132
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
133
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
134
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
135
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
136
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
137
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
138
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
139
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
140
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
141
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
142
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
143
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
147
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
148
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
149
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
150
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
151
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
152
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
163
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
164
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
165
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
170
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
171
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
172
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
173
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
174
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
175
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
176
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
177
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
178
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
179
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
180
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
181
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
182
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
183
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
184
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
185
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
186
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
187
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
188
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
191
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
192
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
193
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
194
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
195
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
196
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
197
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
198
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
199
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
200
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
201
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
202
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
203
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
204
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
205
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
206
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
207
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
208
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
209
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
210
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
211
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
212
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
213
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
214
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
215
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
216
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
217
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
218
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
219
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
220
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
221
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
222
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
223
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
224
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
225
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
226
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
227
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
228
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
229
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
230
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
231
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors"
232
  }
233
  }