DongfuJiang commited on
Commit
c251a89
1 Parent(s): e5489c5

Model save

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: adept/fuyu-8b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: mfuyu_1.5_8b_8192_720p
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # mfuyu_1.5_8b_8192_720p
15
+
16
+ This model is a fine-tuned version of [adept/fuyu-8b](https://huggingface.co/adept/fuyu-8b) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 1e-05
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 1
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 16
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
+ - total_eval_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 1.0
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.39.2
56
+ - Pytorch 2.2.1
57
+ - Datasets 2.18.0
58
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 71013,
5
+ "transformers_version": "4.39.2"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acf81d38756c5eaeb73e2f370bf1a79c054c21f6a8addcd4b22ace654366198
3
+ size 4966836144
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bba3efd375033ebc27bb847a1a3c11d15d5b756437fd5d3d13518e67bca0587
3
+ size 4967399488
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b378331344f472fe0f165e7d3ab37c0ab36c526afb8f8f0b91f7f76de4924d
3
+ size 4967398232
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa5685585766cf6ec6472ac7d94c8fe1d97fcaa7ca525459ee9e1bb3986b024
3
+ size 3914952240
model.safetensors.index.json ADDED
@@ -0,0 +1,589 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18816509952
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.final_layernorm.bias": "model-00004-of-00004.safetensors",
9
+ "language_model.model.final_layernorm.weight": "model-00004-of-00004.safetensors",
10
+ "language_model.model.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.dense.bias": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.dense.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.0.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.0.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.0.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.0.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
33
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
34
+ "language_model.model.layers.1.self_attn.dense.bias": "model-00001-of-00004.safetensors",
35
+ "language_model.model.layers.1.self_attn.dense.weight": "model-00001-of-00004.safetensors",
36
+ "language_model.model.layers.1.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
37
+ "language_model.model.layers.1.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
38
+ "language_model.model.layers.1.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
39
+ "language_model.model.layers.1.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
40
+ "language_model.model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
41
+ "language_model.model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
42
+ "language_model.model.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.10.self_attn.dense.bias": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.10.self_attn.dense.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.10.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.10.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.10.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.10.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.10.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.10.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.11.self_attn.dense.bias": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.11.self_attn.dense.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.11.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.11.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.11.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.11.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.11.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.11.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.12.self_attn.dense.bias": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.12.self_attn.dense.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.12.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.12.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.12.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.12.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.12.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.12.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.13.self_attn.dense.bias": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.13.self_attn.dense.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.13.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.13.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.13.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.13.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.13.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.13.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.14.self_attn.dense.bias": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.14.self_attn.dense.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.14.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.14.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "language_model.model.layers.14.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
119
+ "language_model.model.layers.14.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.model.layers.14.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
121
+ "language_model.model.layers.14.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
122
+ "language_model.model.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
123
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.model.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "language_model.model.layers.15.self_attn.dense.bias": "model-00002-of-00004.safetensors",
131
+ "language_model.model.layers.15.self_attn.dense.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.model.layers.15.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
133
+ "language_model.model.layers.15.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.model.layers.15.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
135
+ "language_model.model.layers.15.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
136
+ "language_model.model.layers.15.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
137
+ "language_model.model.layers.15.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
138
+ "language_model.model.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
139
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
140
+ "language_model.model.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
141
+ "language_model.model.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
142
+ "language_model.model.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
143
+ "language_model.model.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
144
+ "language_model.model.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
145
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
146
+ "language_model.model.layers.16.self_attn.dense.bias": "model-00002-of-00004.safetensors",
147
+ "language_model.model.layers.16.self_attn.dense.weight": "model-00002-of-00004.safetensors",
148
+ "language_model.model.layers.16.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
149
+ "language_model.model.layers.16.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
150
+ "language_model.model.layers.16.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
151
+ "language_model.model.layers.16.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
152
+ "language_model.model.layers.16.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
153
+ "language_model.model.layers.16.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
154
+ "language_model.model.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
155
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
156
+ "language_model.model.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
157
+ "language_model.model.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
158
+ "language_model.model.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
159
+ "language_model.model.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
160
+ "language_model.model.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
161
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
162
+ "language_model.model.layers.17.self_attn.dense.bias": "model-00002-of-00004.safetensors",
163
+ "language_model.model.layers.17.self_attn.dense.weight": "model-00002-of-00004.safetensors",
164
+ "language_model.model.layers.17.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
165
+ "language_model.model.layers.17.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
166
+ "language_model.model.layers.17.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
167
+ "language_model.model.layers.17.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "language_model.model.layers.17.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
169
+ "language_model.model.layers.17.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
170
+ "language_model.model.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
171
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
172
+ "language_model.model.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
173
+ "language_model.model.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
174
+ "language_model.model.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
175
+ "language_model.model.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
176
+ "language_model.model.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
177
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
178
+ "language_model.model.layers.18.self_attn.dense.bias": "model-00002-of-00004.safetensors",
179
+ "language_model.model.layers.18.self_attn.dense.weight": "model-00002-of-00004.safetensors",
180
+ "language_model.model.layers.18.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
181
+ "language_model.model.layers.18.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
182
+ "language_model.model.layers.18.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
183
+ "language_model.model.layers.18.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
184
+ "language_model.model.layers.18.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
185
+ "language_model.model.layers.18.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
186
+ "language_model.model.layers.19.input_layernorm.bias": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.19.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.19.self_attn.dense.bias": "model-00002-of-00004.safetensors",
195
+ "language_model.model.layers.19.self_attn.dense.weight": "model-00002-of-00004.safetensors",
196
+ "language_model.model.layers.19.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
197
+ "language_model.model.layers.19.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
198
+ "language_model.model.layers.19.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
199
+ "language_model.model.layers.19.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
200
+ "language_model.model.layers.19.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
201
+ "language_model.model.layers.19.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
202
+ "language_model.model.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.2.self_attn.dense.bias": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.2.self_attn.dense.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.2.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.2.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.20.input_layernorm.bias": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.20.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.20.self_attn.dense.bias": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.20.self_attn.dense.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.20.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.20.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.20.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.20.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.20.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.20.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.21.self_attn.dense.bias": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.21.self_attn.dense.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.21.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.21.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.21.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.21.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.21.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.21.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.model.layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
251
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.model.layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.22.self_attn.dense.bias": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.22.self_attn.dense.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.22.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
261
+ "language_model.model.layers.22.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
262
+ "language_model.model.layers.22.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
263
+ "language_model.model.layers.22.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
264
+ "language_model.model.layers.22.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
265
+ "language_model.model.layers.22.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
266
+ "language_model.model.layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
267
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
268
+ "language_model.model.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
269
+ "language_model.model.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
270
+ "language_model.model.layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
271
+ "language_model.model.layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
272
+ "language_model.model.layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
273
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.model.layers.23.self_attn.dense.bias": "model-00003-of-00004.safetensors",
275
+ "language_model.model.layers.23.self_attn.dense.weight": "model-00003-of-00004.safetensors",
276
+ "language_model.model.layers.23.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
277
+ "language_model.model.layers.23.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "language_model.model.layers.23.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
279
+ "language_model.model.layers.23.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.model.layers.23.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
281
+ "language_model.model.layers.23.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.model.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
283
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
284
+ "language_model.model.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
285
+ "language_model.model.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
286
+ "language_model.model.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
287
+ "language_model.model.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
288
+ "language_model.model.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
289
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
290
+ "language_model.model.layers.24.self_attn.dense.bias": "model-00003-of-00004.safetensors",
291
+ "language_model.model.layers.24.self_attn.dense.weight": "model-00003-of-00004.safetensors",
292
+ "language_model.model.layers.24.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
293
+ "language_model.model.layers.24.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
294
+ "language_model.model.layers.24.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
295
+ "language_model.model.layers.24.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "language_model.model.layers.24.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
297
+ "language_model.model.layers.24.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
298
+ "language_model.model.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
299
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "language_model.model.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
301
+ "language_model.model.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
302
+ "language_model.model.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
303
+ "language_model.model.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
304
+ "language_model.model.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
305
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
306
+ "language_model.model.layers.25.self_attn.dense.bias": "model-00003-of-00004.safetensors",
307
+ "language_model.model.layers.25.self_attn.dense.weight": "model-00003-of-00004.safetensors",
308
+ "language_model.model.layers.25.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
309
+ "language_model.model.layers.25.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
310
+ "language_model.model.layers.25.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
311
+ "language_model.model.layers.25.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
312
+ "language_model.model.layers.25.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
313
+ "language_model.model.layers.25.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
314
+ "language_model.model.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
315
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
316
+ "language_model.model.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
317
+ "language_model.model.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
318
+ "language_model.model.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
319
+ "language_model.model.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
320
+ "language_model.model.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
321
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
322
+ "language_model.model.layers.26.self_attn.dense.bias": "model-00003-of-00004.safetensors",
323
+ "language_model.model.layers.26.self_attn.dense.weight": "model-00003-of-00004.safetensors",
324
+ "language_model.model.layers.26.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
325
+ "language_model.model.layers.26.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
326
+ "language_model.model.layers.26.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
327
+ "language_model.model.layers.26.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
328
+ "language_model.model.layers.26.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
329
+ "language_model.model.layers.26.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
330
+ "language_model.model.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
331
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
332
+ "language_model.model.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
333
+ "language_model.model.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
334
+ "language_model.model.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
335
+ "language_model.model.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
336
+ "language_model.model.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
337
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
338
+ "language_model.model.layers.27.self_attn.dense.bias": "model-00003-of-00004.safetensors",
339
+ "language_model.model.layers.27.self_attn.dense.weight": "model-00003-of-00004.safetensors",
340
+ "language_model.model.layers.27.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
341
+ "language_model.model.layers.27.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
342
+ "language_model.model.layers.27.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
343
+ "language_model.model.layers.27.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
344
+ "language_model.model.layers.27.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
345
+ "language_model.model.layers.27.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
346
+ "language_model.model.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
347
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
348
+ "language_model.model.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
349
+ "language_model.model.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
350
+ "language_model.model.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
351
+ "language_model.model.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
352
+ "language_model.model.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
353
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
354
+ "language_model.model.layers.28.self_attn.dense.bias": "model-00003-of-00004.safetensors",
355
+ "language_model.model.layers.28.self_attn.dense.weight": "model-00003-of-00004.safetensors",
356
+ "language_model.model.layers.28.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
357
+ "language_model.model.layers.28.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
358
+ "language_model.model.layers.28.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
359
+ "language_model.model.layers.28.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
360
+ "language_model.model.layers.28.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
361
+ "language_model.model.layers.28.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
362
+ "language_model.model.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
363
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
364
+ "language_model.model.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
365
+ "language_model.model.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
366
+ "language_model.model.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
367
+ "language_model.model.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
368
+ "language_model.model.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
369
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
370
+ "language_model.model.layers.29.self_attn.dense.bias": "model-00003-of-00004.safetensors",
371
+ "language_model.model.layers.29.self_attn.dense.weight": "model-00003-of-00004.safetensors",
372
+ "language_model.model.layers.29.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
373
+ "language_model.model.layers.29.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
374
+ "language_model.model.layers.29.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
375
+ "language_model.model.layers.29.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
376
+ "language_model.model.layers.29.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
377
+ "language_model.model.layers.29.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
378
+ "language_model.model.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
379
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
380
+ "language_model.model.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
381
+ "language_model.model.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
382
+ "language_model.model.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
383
+ "language_model.model.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
384
+ "language_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
385
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "language_model.model.layers.3.self_attn.dense.bias": "model-00001-of-00004.safetensors",
387
+ "language_model.model.layers.3.self_attn.dense.weight": "model-00001-of-00004.safetensors",
388
+ "language_model.model.layers.3.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
389
+ "language_model.model.layers.3.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
390
+ "language_model.model.layers.3.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
391
+ "language_model.model.layers.3.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
392
+ "language_model.model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
393
+ "language_model.model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
394
+ "language_model.model.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
395
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
396
+ "language_model.model.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
397
+ "language_model.model.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
398
+ "language_model.model.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
399
+ "language_model.model.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
400
+ "language_model.model.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
401
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
402
+ "language_model.model.layers.30.self_attn.dense.bias": "model-00003-of-00004.safetensors",
403
+ "language_model.model.layers.30.self_attn.dense.weight": "model-00003-of-00004.safetensors",
404
+ "language_model.model.layers.30.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
405
+ "language_model.model.layers.30.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
406
+ "language_model.model.layers.30.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
407
+ "language_model.model.layers.30.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
408
+ "language_model.model.layers.30.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
409
+ "language_model.model.layers.30.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
410
+ "language_model.model.layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
411
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
412
+ "language_model.model.layers.31.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
413
+ "language_model.model.layers.31.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
414
+ "language_model.model.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
415
+ "language_model.model.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
416
+ "language_model.model.layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
417
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
418
+ "language_model.model.layers.31.self_attn.dense.bias": "model-00003-of-00004.safetensors",
419
+ "language_model.model.layers.31.self_attn.dense.weight": "model-00003-of-00004.safetensors",
420
+ "language_model.model.layers.31.self_attn.k_layernorm.bias": "model-00003-of-00004.safetensors",
421
+ "language_model.model.layers.31.self_attn.k_layernorm.weight": "model-00003-of-00004.safetensors",
422
+ "language_model.model.layers.31.self_attn.q_layernorm.bias": "model-00003-of-00004.safetensors",
423
+ "language_model.model.layers.31.self_attn.q_layernorm.weight": "model-00003-of-00004.safetensors",
424
+ "language_model.model.layers.31.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
425
+ "language_model.model.layers.31.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
426
+ "language_model.model.layers.32.input_layernorm.bias": "model-00004-of-00004.safetensors",
427
+ "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
428
+ "language_model.model.layers.32.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
429
+ "language_model.model.layers.32.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
430
+ "language_model.model.layers.32.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
431
+ "language_model.model.layers.32.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
432
+ "language_model.model.layers.32.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
433
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
434
+ "language_model.model.layers.32.self_attn.dense.bias": "model-00004-of-00004.safetensors",
435
+ "language_model.model.layers.32.self_attn.dense.weight": "model-00004-of-00004.safetensors",
436
+ "language_model.model.layers.32.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
437
+ "language_model.model.layers.32.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
438
+ "language_model.model.layers.32.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
439
+ "language_model.model.layers.32.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
440
+ "language_model.model.layers.32.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
441
+ "language_model.model.layers.32.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
442
+ "language_model.model.layers.33.input_layernorm.bias": "model-00004-of-00004.safetensors",
443
+ "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
444
+ "language_model.model.layers.33.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
445
+ "language_model.model.layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
446
+ "language_model.model.layers.33.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
447
+ "language_model.model.layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
448
+ "language_model.model.layers.33.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
449
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
450
+ "language_model.model.layers.33.self_attn.dense.bias": "model-00004-of-00004.safetensors",
451
+ "language_model.model.layers.33.self_attn.dense.weight": "model-00004-of-00004.safetensors",
452
+ "language_model.model.layers.33.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
453
+ "language_model.model.layers.33.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
454
+ "language_model.model.layers.33.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
455
+ "language_model.model.layers.33.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
456
+ "language_model.model.layers.33.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
457
+ "language_model.model.layers.33.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
458
+ "language_model.model.layers.34.input_layernorm.bias": "model-00004-of-00004.safetensors",
459
+ "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
460
+ "language_model.model.layers.34.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
461
+ "language_model.model.layers.34.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
462
+ "language_model.model.layers.34.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
463
+ "language_model.model.layers.34.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
464
+ "language_model.model.layers.34.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
465
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
466
+ "language_model.model.layers.34.self_attn.dense.bias": "model-00004-of-00004.safetensors",
467
+ "language_model.model.layers.34.self_attn.dense.weight": "model-00004-of-00004.safetensors",
468
+ "language_model.model.layers.34.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
469
+ "language_model.model.layers.34.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
470
+ "language_model.model.layers.34.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
471
+ "language_model.model.layers.34.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
472
+ "language_model.model.layers.34.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
473
+ "language_model.model.layers.34.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
474
+ "language_model.model.layers.35.input_layernorm.bias": "model-00004-of-00004.safetensors",
475
+ "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
476
+ "language_model.model.layers.35.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
477
+ "language_model.model.layers.35.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
478
+ "language_model.model.layers.35.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
479
+ "language_model.model.layers.35.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
480
+ "language_model.model.layers.35.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
481
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
482
+ "language_model.model.layers.35.self_attn.dense.bias": "model-00004-of-00004.safetensors",
483
+ "language_model.model.layers.35.self_attn.dense.weight": "model-00004-of-00004.safetensors",
484
+ "language_model.model.layers.35.self_attn.k_layernorm.bias": "model-00004-of-00004.safetensors",
485
+ "language_model.model.layers.35.self_attn.k_layernorm.weight": "model-00004-of-00004.safetensors",
486
+ "language_model.model.layers.35.self_attn.q_layernorm.bias": "model-00004-of-00004.safetensors",
487
+ "language_model.model.layers.35.self_attn.q_layernorm.weight": "model-00004-of-00004.safetensors",
488
+ "language_model.model.layers.35.self_attn.query_key_value.bias": "model-00004-of-00004.safetensors",
489
+ "language_model.model.layers.35.self_attn.query_key_value.weight": "model-00004-of-00004.safetensors",
490
+ "language_model.model.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
491
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
492
+ "language_model.model.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
493
+ "language_model.model.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
494
+ "language_model.model.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
495
+ "language_model.model.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
496
+ "language_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
497
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
498
+ "language_model.model.layers.4.self_attn.dense.bias": "model-00001-of-00004.safetensors",
499
+ "language_model.model.layers.4.self_attn.dense.weight": "model-00001-of-00004.safetensors",
500
+ "language_model.model.layers.4.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
501
+ "language_model.model.layers.4.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
502
+ "language_model.model.layers.4.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
503
+ "language_model.model.layers.4.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
504
+ "language_model.model.layers.4.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
505
+ "language_model.model.layers.4.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
506
+ "language_model.model.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
507
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
508
+ "language_model.model.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
509
+ "language_model.model.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
510
+ "language_model.model.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
511
+ "language_model.model.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
512
+ "language_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
513
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
514
+ "language_model.model.layers.5.self_attn.dense.bias": "model-00001-of-00004.safetensors",
515
+ "language_model.model.layers.5.self_attn.dense.weight": "model-00001-of-00004.safetensors",
516
+ "language_model.model.layers.5.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
517
+ "language_model.model.layers.5.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
518
+ "language_model.model.layers.5.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
519
+ "language_model.model.layers.5.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
520
+ "language_model.model.layers.5.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
521
+ "language_model.model.layers.5.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
522
+ "language_model.model.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
523
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
524
+ "language_model.model.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
525
+ "language_model.model.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
526
+ "language_model.model.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
527
+ "language_model.model.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
528
+ "language_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
529
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
530
+ "language_model.model.layers.6.self_attn.dense.bias": "model-00001-of-00004.safetensors",
531
+ "language_model.model.layers.6.self_attn.dense.weight": "model-00001-of-00004.safetensors",
532
+ "language_model.model.layers.6.self_attn.k_layernorm.bias": "model-00001-of-00004.safetensors",
533
+ "language_model.model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00004.safetensors",
534
+ "language_model.model.layers.6.self_attn.q_layernorm.bias": "model-00001-of-00004.safetensors",
535
+ "language_model.model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00004.safetensors",
536
+ "language_model.model.layers.6.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
537
+ "language_model.model.layers.6.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
538
+ "language_model.model.layers.7.input_layernorm.bias": "model-00002-of-00004.safetensors",
539
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
540
+ "language_model.model.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
541
+ "language_model.model.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
542
+ "language_model.model.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
543
+ "language_model.model.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
544
+ "language_model.model.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
545
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
546
+ "language_model.model.layers.7.self_attn.dense.bias": "model-00002-of-00004.safetensors",
547
+ "language_model.model.layers.7.self_attn.dense.weight": "model-00002-of-00004.safetensors",
548
+ "language_model.model.layers.7.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
549
+ "language_model.model.layers.7.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
550
+ "language_model.model.layers.7.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
551
+ "language_model.model.layers.7.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
552
+ "language_model.model.layers.7.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
553
+ "language_model.model.layers.7.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
554
+ "language_model.model.layers.8.input_layernorm.bias": "model-00002-of-00004.safetensors",
555
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
556
+ "language_model.model.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
557
+ "language_model.model.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
558
+ "language_model.model.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
559
+ "language_model.model.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
560
+ "language_model.model.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
561
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
562
+ "language_model.model.layers.8.self_attn.dense.bias": "model-00002-of-00004.safetensors",
563
+ "language_model.model.layers.8.self_attn.dense.weight": "model-00002-of-00004.safetensors",
564
+ "language_model.model.layers.8.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
565
+ "language_model.model.layers.8.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
566
+ "language_model.model.layers.8.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
567
+ "language_model.model.layers.8.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
568
+ "language_model.model.layers.8.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
569
+ "language_model.model.layers.8.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
570
+ "language_model.model.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
571
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
572
+ "language_model.model.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
573
+ "language_model.model.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
574
+ "language_model.model.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
575
+ "language_model.model.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
576
+ "language_model.model.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
577
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
578
+ "language_model.model.layers.9.self_attn.dense.bias": "model-00002-of-00004.safetensors",
579
+ "language_model.model.layers.9.self_attn.dense.weight": "model-00002-of-00004.safetensors",
580
+ "language_model.model.layers.9.self_attn.k_layernorm.bias": "model-00002-of-00004.safetensors",
581
+ "language_model.model.layers.9.self_attn.k_layernorm.weight": "model-00002-of-00004.safetensors",
582
+ "language_model.model.layers.9.self_attn.q_layernorm.bias": "model-00002-of-00004.safetensors",
583
+ "language_model.model.layers.9.self_attn.q_layernorm.weight": "model-00002-of-00004.safetensors",
584
+ "language_model.model.layers.9.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
585
+ "language_model.model.layers.9.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
586
+ "vision_embed_tokens.bias": "model-00004-of-00004.safetensors",
587
+ "vision_embed_tokens.weight": "model-00004-of-00004.safetensors"
588
+ }
589
+ }