Hugging Face's logo

yale-nlp
/
MDCureRM

Safetensors
English
RewardModel
reward model
fine-grained
Model card Files Community
1
pybeebee commited on
Commit
eb0a070
•
1 Parent(s): 2ddce44

Upload model

Browse files
Files changed (10) hide show
  1. config.json +31 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00007.safetensors +3 -0
  4. model-00002-of-00007.safetensors +3 -0
  5. model-00003-of-00007.safetensors +3 -0
  6. model-00004-of-00007.safetensors +3 -0
  7. model-00005-of-00007.safetensors +3 -0
  8. model-00006-of-00007.safetensors +3 -0
  9. model-00007-of-00007.safetensors +3 -0
  10. model.safetensors.index.json +299 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/gkl7/multidoc1/multidoc-instr-tune-longt5b/ppo/reward_model_train/results_FINAL/real_1e-3/final_model",
3
+ "architectures": [
4
+ "RewardModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "base_model_name": "sfairXC/FsfairX-LLaMA3-RM-v0.1",
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "RewardModel",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "pretraining_tp": 1,
22
+ "reward_dim": 6,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.44.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.1"
6
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419e02d0019abe3522c89591911f2544c11b9389281ecb99b8b82dd6eab06c82
3
+ size 4886482712
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380c954604b2baa8cd24e22bd9c4facba380ccb41c80024eac678c233bfcac05
3
+ size 4832007688
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87af28ed93de4627a514feadbd36c7a9c9c32db70fa9b3ce2360ac574ff21e54
3
+ size 4999813376
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b88bb3ef78fa6e7097a511b8de203a627f0bf1b83cc9a49746e997914d167ab
3
+ size 4999813392
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd0dbeda1b7d2fff92b316dd18fd13f4fa5ee29e2f5c6fedf8d78e184cc0ab5
3
+ size 4832007736
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99718c20fffdd6343b385b26edd7406fcb61f2329c1d2b2423eae855e5408b9a
3
+ size 4999813392
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c668cf73575eee3c0b6b9f4ddb32cb05d4ad028bff6dbb327040ff2f0e6e80
3
+ size 469910304
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 30019813400
4
+ },
5
+ "weight_map": {
6
+ "BASE_MODEL.embed_tokens.weight": "model-00001-of-00007.safetensors",
7
+ "BASE_MODEL.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
8
+ "BASE_MODEL.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
9
+ "BASE_MODEL.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
10
+ "BASE_MODEL.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
11
+ "BASE_MODEL.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
12
+ "BASE_MODEL.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
13
+ "BASE_MODEL.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
14
+ "BASE_MODEL.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
15
+ "BASE_MODEL.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
16
+ "BASE_MODEL.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
17
+ "BASE_MODEL.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
18
+ "BASE_MODEL.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
19
+ "BASE_MODEL.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
20
+ "BASE_MODEL.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
21
+ "BASE_MODEL.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
22
+ "BASE_MODEL.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
23
+ "BASE_MODEL.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
24
+ "BASE_MODEL.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
25
+ "BASE_MODEL.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
26
+ "BASE_MODEL.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
27
+ "BASE_MODEL.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
28
+ "BASE_MODEL.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
29
+ "BASE_MODEL.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
30
+ "BASE_MODEL.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
31
+ "BASE_MODEL.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
32
+ "BASE_MODEL.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
33
+ "BASE_MODEL.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
34
+ "BASE_MODEL.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
35
+ "BASE_MODEL.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
36
+ "BASE_MODEL.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
37
+ "BASE_MODEL.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
38
+ "BASE_MODEL.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
39
+ "BASE_MODEL.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "BASE_MODEL.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "BASE_MODEL.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
42
+ "BASE_MODEL.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
43
+ "BASE_MODEL.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
44
+ "BASE_MODEL.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
45
+ "BASE_MODEL.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
46
+ "BASE_MODEL.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
47
+ "BASE_MODEL.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
48
+ "BASE_MODEL.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
49
+ "BASE_MODEL.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
50
+ "BASE_MODEL.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
51
+ "BASE_MODEL.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
52
+ "BASE_MODEL.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
53
+ "BASE_MODEL.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
54
+ "BASE_MODEL.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
55
+ "BASE_MODEL.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
56
+ "BASE_MODEL.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
57
+ "BASE_MODEL.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
58
+ "BASE_MODEL.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
59
+ "BASE_MODEL.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
60
+ "BASE_MODEL.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
61
+ "BASE_MODEL.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
62
+ "BASE_MODEL.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
63
+ "BASE_MODEL.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
64
+ "BASE_MODEL.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
65
+ "BASE_MODEL.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
66
+ "BASE_MODEL.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
67
+ "BASE_MODEL.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
68
+ "BASE_MODEL.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
69
+ "BASE_MODEL.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
70
+ "BASE_MODEL.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
71
+ "BASE_MODEL.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
72
+ "BASE_MODEL.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
73
+ "BASE_MODEL.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
74
+ "BASE_MODEL.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
75
+ "BASE_MODEL.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
76
+ "BASE_MODEL.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
77
+ "BASE_MODEL.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
78
+ "BASE_MODEL.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
79
+ "BASE_MODEL.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
80
+ "BASE_MODEL.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
81
+ "BASE_MODEL.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
82
+ "BASE_MODEL.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
83
+ "BASE_MODEL.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
84
+ "BASE_MODEL.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
85
+ "BASE_MODEL.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
86
+ "BASE_MODEL.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
87
+ "BASE_MODEL.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
88
+ "BASE_MODEL.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
89
+ "BASE_MODEL.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
90
+ "BASE_MODEL.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
91
+ "BASE_MODEL.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
92
+ "BASE_MODEL.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
93
+ "BASE_MODEL.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
94
+ "BASE_MODEL.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
95
+ "BASE_MODEL.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
96
+ "BASE_MODEL.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
97
+ "BASE_MODEL.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "BASE_MODEL.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
99
+ "BASE_MODEL.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
100
+ "BASE_MODEL.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
101
+ "BASE_MODEL.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
102
+ "BASE_MODEL.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
103
+ "BASE_MODEL.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
104
+ "BASE_MODEL.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
105
+ "BASE_MODEL.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
106
+ "BASE_MODEL.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
107
+ "BASE_MODEL.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
108
+ "BASE_MODEL.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
109
+ "BASE_MODEL.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
110
+ "BASE_MODEL.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
111
+ "BASE_MODEL.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "BASE_MODEL.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
113
+ "BASE_MODEL.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
114
+ "BASE_MODEL.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
115
+ "BASE_MODEL.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
116
+ "BASE_MODEL.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
117
+ "BASE_MODEL.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
118
+ "BASE_MODEL.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
119
+ "BASE_MODEL.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
120
+ "BASE_MODEL.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
121
+ "BASE_MODEL.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
122
+ "BASE_MODEL.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
123
+ "BASE_MODEL.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
124
+ "BASE_MODEL.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
125
+ "BASE_MODEL.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
126
+ "BASE_MODEL.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
127
+ "BASE_MODEL.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
128
+ "BASE_MODEL.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
129
+ "BASE_MODEL.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
130
+ "BASE_MODEL.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
131
+ "BASE_MODEL.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
132
+ "BASE_MODEL.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
133
+ "BASE_MODEL.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "BASE_MODEL.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
135
+ "BASE_MODEL.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
136
+ "BASE_MODEL.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
137
+ "BASE_MODEL.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
138
+ "BASE_MODEL.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
139
+ "BASE_MODEL.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
140
+ "BASE_MODEL.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
141
+ "BASE_MODEL.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
142
+ "BASE_MODEL.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
143
+ "BASE_MODEL.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
144
+ "BASE_MODEL.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
145
+ "BASE_MODEL.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
146
+ "BASE_MODEL.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
147
+ "BASE_MODEL.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "BASE_MODEL.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "BASE_MODEL.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
150
+ "BASE_MODEL.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
151
+ "BASE_MODEL.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
152
+ "BASE_MODEL.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
153
+ "BASE_MODEL.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
154
+ "BASE_MODEL.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
155
+ "BASE_MODEL.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
156
+ "BASE_MODEL.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
157
+ "BASE_MODEL.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
158
+ "BASE_MODEL.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
159
+ "BASE_MODEL.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
160
+ "BASE_MODEL.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
161
+ "BASE_MODEL.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
162
+ "BASE_MODEL.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
163
+ "BASE_MODEL.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
164
+ "BASE_MODEL.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
165
+ "BASE_MODEL.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
166
+ "BASE_MODEL.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
167
+ "BASE_MODEL.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
168
+ "BASE_MODEL.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
169
+ "BASE_MODEL.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
170
+ "BASE_MODEL.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
171
+ "BASE_MODEL.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
172
+ "BASE_MODEL.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
173
+ "BASE_MODEL.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
174
+ "BASE_MODEL.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
175
+ "BASE_MODEL.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
176
+ "BASE_MODEL.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
177
+ "BASE_MODEL.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
178
+ "BASE_MODEL.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
179
+ "BASE_MODEL.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
180
+ "BASE_MODEL.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
181
+ "BASE_MODEL.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
182
+ "BASE_MODEL.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
183
+ "BASE_MODEL.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
184
+ "BASE_MODEL.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
185
+ "BASE_MODEL.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
186
+ "BASE_MODEL.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
187
+ "BASE_MODEL.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
188
+ "BASE_MODEL.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
189
+ "BASE_MODEL.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
190
+ "BASE_MODEL.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
191
+ "BASE_MODEL.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
192
+ "BASE_MODEL.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
193
+ "BASE_MODEL.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
194
+ "BASE_MODEL.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
195
+ "BASE_MODEL.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
196
+ "BASE_MODEL.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
197
+ "BASE_MODEL.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
198
+ "BASE_MODEL.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
199
+ "BASE_MODEL.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
200
+ "BASE_MODEL.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
201
+ "BASE_MODEL.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
202
+ "BASE_MODEL.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
203
+ "BASE_MODEL.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
204
+ "BASE_MODEL.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
205
+ "BASE_MODEL.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
206
+ "BASE_MODEL.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
207
+ "BASE_MODEL.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
208
+ "BASE_MODEL.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
209
+ "BASE_MODEL.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
210
+ "BASE_MODEL.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
211
+ "BASE_MODEL.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
212
+ "BASE_MODEL.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
213
+ "BASE_MODEL.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
214
+ "BASE_MODEL.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
215
+ "BASE_MODEL.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
216
+ "BASE_MODEL.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
217
+ "BASE_MODEL.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
218
+ "BASE_MODEL.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
219
+ "BASE_MODEL.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
220
+ "BASE_MODEL.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
221
+ "BASE_MODEL.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
222
+ "BASE_MODEL.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
223
+ "BASE_MODEL.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
224
+ "BASE_MODEL.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
225
+ "BASE_MODEL.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
226
+ "BASE_MODEL.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
227
+ "BASE_MODEL.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
228
+ "BASE_MODEL.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
229
+ "BASE_MODEL.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
230
+ "BASE_MODEL.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
231
+ "BASE_MODEL.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
232
+ "BASE_MODEL.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
233
+ "BASE_MODEL.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
234
+ "BASE_MODEL.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
235
+ "BASE_MODEL.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
236
+ "BASE_MODEL.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
237
+ "BASE_MODEL.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
238
+ "BASE_MODEL.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
239
+ "BASE_MODEL.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
240
+ "BASE_MODEL.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
241
+ "BASE_MODEL.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
242
+ "BASE_MODEL.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
243
+ "BASE_MODEL.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
244
+ "BASE_MODEL.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
245
+ "BASE_MODEL.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
246
+ "BASE_MODEL.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
247
+ "BASE_MODEL.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
248
+ "BASE_MODEL.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
249
+ "BASE_MODEL.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
250
+ "BASE_MODEL.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
251
+ "BASE_MODEL.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
252
+ "BASE_MODEL.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
253
+ "BASE_MODEL.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
254
+ "BASE_MODEL.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
255
+ "BASE_MODEL.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
256
+ "BASE_MODEL.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
257
+ "BASE_MODEL.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
258
+ "BASE_MODEL.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
259
+ "BASE_MODEL.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
260
+ "BASE_MODEL.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
261
+ "BASE_MODEL.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
262
+ "BASE_MODEL.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
263
+ "BASE_MODEL.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
264
+ "BASE_MODEL.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
265
+ "BASE_MODEL.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
266
+ "BASE_MODEL.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
267
+ "BASE_MODEL.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
268
+ "BASE_MODEL.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
269
+ "BASE_MODEL.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
270
+ "BASE_MODEL.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
271
+ "BASE_MODEL.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
272
+ "BASE_MODEL.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
273
+ "BASE_MODEL.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
274
+ "BASE_MODEL.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
275
+ "BASE_MODEL.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
276
+ "BASE_MODEL.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
277
+ "BASE_MODEL.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
278
+ "BASE_MODEL.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
279
+ "BASE_MODEL.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
280
+ "BASE_MODEL.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
281
+ "BASE_MODEL.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
282
+ "BASE_MODEL.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
283
+ "BASE_MODEL.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
284
+ "BASE_MODEL.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
285
+ "BASE_MODEL.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
286
+ "BASE_MODEL.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
287
+ "BASE_MODEL.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
288
+ "BASE_MODEL.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
289
+ "BASE_MODEL.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
290
+ "BASE_MODEL.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
291
+ "BASE_MODEL.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
292
+ "BASE_MODEL.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
293
+ "BASE_MODEL.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
294
+ "BASE_MODEL.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
295
+ "BASE_MODEL.norm.weight": "model-00007-of-00007.safetensors",
296
+ "regression_head.bias": "model-00007-of-00007.safetensors",
297
+ "regression_head.weight": "model-00007-of-00007.safetensors"
298
+ }
299
+ }