Hugging Face's logo

iqrakiran
/
custom_mental-falcon-7b-instruct-custom-ds-101-200

Text Generation
Transformers
Safetensors
falcon
trl
sft
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
iqrakiran commited on
Commit
f431df5
•
1 Parent(s): 6e4fcea

Upload FalconForCausalLM

Browse files
Files changed (4) hide show
  1. adapter_model-00001-of-00003.safetensors +3 -0
  2. adapter_model-00002-of-00003.safetensors +3 -0
  3. adapter_model-00003-of-00003.safetensors +3 -0
  4. model.safetensors.index.json +263 -0
adapter_model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7868c868e59cff543aa66b86384270fa9352011a22c862b0e3444f477d11f544
3
+ size 199358176
adapter_model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b51d6f68fe4298cb3805eb665155730974a4a2d32a1624d55e40cfd28048f8
3
+ size 198162064
adapter_model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b86531f02b3dae66264ceb6076a88940a649ef16cdb479365691bbd838abae
3
+ size 124707008
model.safetensors.index.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 522190848
4
+ },
5
+ "weight_map": {
6
+ "base_model.model.transformer.h.0.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
7
+ "base_model.model.transformer.h.0.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
8
+ "base_model.model.transformer.h.0.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
9
+ "base_model.model.transformer.h.0.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
10
+ "base_model.model.transformer.h.0.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
11
+ "base_model.model.transformer.h.0.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
12
+ "base_model.model.transformer.h.0.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
13
+ "base_model.model.transformer.h.0.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
14
+ "base_model.model.transformer.h.1.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
15
+ "base_model.model.transformer.h.1.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
16
+ "base_model.model.transformer.h.1.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
17
+ "base_model.model.transformer.h.1.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
18
+ "base_model.model.transformer.h.1.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
19
+ "base_model.model.transformer.h.1.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
20
+ "base_model.model.transformer.h.1.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
21
+ "base_model.model.transformer.h.1.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
22
+ "base_model.model.transformer.h.10.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
23
+ "base_model.model.transformer.h.10.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
24
+ "base_model.model.transformer.h.10.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
25
+ "base_model.model.transformer.h.10.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
26
+ "base_model.model.transformer.h.10.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
27
+ "base_model.model.transformer.h.10.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
28
+ "base_model.model.transformer.h.10.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
29
+ "base_model.model.transformer.h.10.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
30
+ "base_model.model.transformer.h.11.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
31
+ "base_model.model.transformer.h.11.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
32
+ "base_model.model.transformer.h.11.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
33
+ "base_model.model.transformer.h.11.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
34
+ "base_model.model.transformer.h.11.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
35
+ "base_model.model.transformer.h.11.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
36
+ "base_model.model.transformer.h.11.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
37
+ "base_model.model.transformer.h.11.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
38
+ "base_model.model.transformer.h.12.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
39
+ "base_model.model.transformer.h.12.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
40
+ "base_model.model.transformer.h.12.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
41
+ "base_model.model.transformer.h.12.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
42
+ "base_model.model.transformer.h.12.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
43
+ "base_model.model.transformer.h.12.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
44
+ "base_model.model.transformer.h.12.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
45
+ "base_model.model.transformer.h.12.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
46
+ "base_model.model.transformer.h.13.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
47
+ "base_model.model.transformer.h.13.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
48
+ "base_model.model.transformer.h.13.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
49
+ "base_model.model.transformer.h.13.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
50
+ "base_model.model.transformer.h.13.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
51
+ "base_model.model.transformer.h.13.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
52
+ "base_model.model.transformer.h.13.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
53
+ "base_model.model.transformer.h.13.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
54
+ "base_model.model.transformer.h.14.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
55
+ "base_model.model.transformer.h.14.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
56
+ "base_model.model.transformer.h.14.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
57
+ "base_model.model.transformer.h.14.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
58
+ "base_model.model.transformer.h.14.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
59
+ "base_model.model.transformer.h.14.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
60
+ "base_model.model.transformer.h.14.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
61
+ "base_model.model.transformer.h.14.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
62
+ "base_model.model.transformer.h.15.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
63
+ "base_model.model.transformer.h.15.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
64
+ "base_model.model.transformer.h.15.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
65
+ "base_model.model.transformer.h.15.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
66
+ "base_model.model.transformer.h.15.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
67
+ "base_model.model.transformer.h.15.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
68
+ "base_model.model.transformer.h.15.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
69
+ "base_model.model.transformer.h.15.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
70
+ "base_model.model.transformer.h.16.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
71
+ "base_model.model.transformer.h.16.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
72
+ "base_model.model.transformer.h.16.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
73
+ "base_model.model.transformer.h.16.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
74
+ "base_model.model.transformer.h.16.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
75
+ "base_model.model.transformer.h.16.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
76
+ "base_model.model.transformer.h.16.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
77
+ "base_model.model.transformer.h.16.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
78
+ "base_model.model.transformer.h.17.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
79
+ "base_model.model.transformer.h.17.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
80
+ "base_model.model.transformer.h.17.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
81
+ "base_model.model.transformer.h.17.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
82
+ "base_model.model.transformer.h.17.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
83
+ "base_model.model.transformer.h.17.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
84
+ "base_model.model.transformer.h.17.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
85
+ "base_model.model.transformer.h.17.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
86
+ "base_model.model.transformer.h.18.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
87
+ "base_model.model.transformer.h.18.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
88
+ "base_model.model.transformer.h.18.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
89
+ "base_model.model.transformer.h.18.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
90
+ "base_model.model.transformer.h.18.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
91
+ "base_model.model.transformer.h.18.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
92
+ "base_model.model.transformer.h.18.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
93
+ "base_model.model.transformer.h.18.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
94
+ "base_model.model.transformer.h.19.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
95
+ "base_model.model.transformer.h.19.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
96
+ "base_model.model.transformer.h.19.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
97
+ "base_model.model.transformer.h.19.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
98
+ "base_model.model.transformer.h.19.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
99
+ "base_model.model.transformer.h.19.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
100
+ "base_model.model.transformer.h.19.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
101
+ "base_model.model.transformer.h.19.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
102
+ "base_model.model.transformer.h.2.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
103
+ "base_model.model.transformer.h.2.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
104
+ "base_model.model.transformer.h.2.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
105
+ "base_model.model.transformer.h.2.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
106
+ "base_model.model.transformer.h.2.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
107
+ "base_model.model.transformer.h.2.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
108
+ "base_model.model.transformer.h.2.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
109
+ "base_model.model.transformer.h.2.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
110
+ "base_model.model.transformer.h.20.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
111
+ "base_model.model.transformer.h.20.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
112
+ "base_model.model.transformer.h.20.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
113
+ "base_model.model.transformer.h.20.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
114
+ "base_model.model.transformer.h.20.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
115
+ "base_model.model.transformer.h.20.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
116
+ "base_model.model.transformer.h.20.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
117
+ "base_model.model.transformer.h.20.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
118
+ "base_model.model.transformer.h.21.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
119
+ "base_model.model.transformer.h.21.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
120
+ "base_model.model.transformer.h.21.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
121
+ "base_model.model.transformer.h.21.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
122
+ "base_model.model.transformer.h.21.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
123
+ "base_model.model.transformer.h.21.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
124
+ "base_model.model.transformer.h.21.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
125
+ "base_model.model.transformer.h.21.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
126
+ "base_model.model.transformer.h.22.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
127
+ "base_model.model.transformer.h.22.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
128
+ "base_model.model.transformer.h.22.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
129
+ "base_model.model.transformer.h.22.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
130
+ "base_model.model.transformer.h.22.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
131
+ "base_model.model.transformer.h.22.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
132
+ "base_model.model.transformer.h.22.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
133
+ "base_model.model.transformer.h.22.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
134
+ "base_model.model.transformer.h.23.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
135
+ "base_model.model.transformer.h.23.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
136
+ "base_model.model.transformer.h.23.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
137
+ "base_model.model.transformer.h.23.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
138
+ "base_model.model.transformer.h.23.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
139
+ "base_model.model.transformer.h.23.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
140
+ "base_model.model.transformer.h.23.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
141
+ "base_model.model.transformer.h.23.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
142
+ "base_model.model.transformer.h.24.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
143
+ "base_model.model.transformer.h.24.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
144
+ "base_model.model.transformer.h.24.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
145
+ "base_model.model.transformer.h.24.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
146
+ "base_model.model.transformer.h.24.self_attention.dense.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
147
+ "base_model.model.transformer.h.24.self_attention.dense.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
148
+ "base_model.model.transformer.h.24.self_attention.query_key_value.lora_A.weight": "adapter_model-00002-of-00003.safetensors",
149
+ "base_model.model.transformer.h.24.self_attention.query_key_value.lora_B.weight": "adapter_model-00002-of-00003.safetensors",
150
+ "base_model.model.transformer.h.25.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
151
+ "base_model.model.transformer.h.25.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
152
+ "base_model.model.transformer.h.25.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
153
+ "base_model.model.transformer.h.25.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
154
+ "base_model.model.transformer.h.25.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
155
+ "base_model.model.transformer.h.25.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
156
+ "base_model.model.transformer.h.25.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
157
+ "base_model.model.transformer.h.25.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
158
+ "base_model.model.transformer.h.26.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
159
+ "base_model.model.transformer.h.26.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
160
+ "base_model.model.transformer.h.26.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
161
+ "base_model.model.transformer.h.26.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
162
+ "base_model.model.transformer.h.26.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
163
+ "base_model.model.transformer.h.26.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
164
+ "base_model.model.transformer.h.26.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
165
+ "base_model.model.transformer.h.26.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
166
+ "base_model.model.transformer.h.27.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
167
+ "base_model.model.transformer.h.27.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
168
+ "base_model.model.transformer.h.27.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
169
+ "base_model.model.transformer.h.27.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
170
+ "base_model.model.transformer.h.27.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
171
+ "base_model.model.transformer.h.27.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
172
+ "base_model.model.transformer.h.27.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
173
+ "base_model.model.transformer.h.27.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
174
+ "base_model.model.transformer.h.28.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
175
+ "base_model.model.transformer.h.28.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
176
+ "base_model.model.transformer.h.28.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
177
+ "base_model.model.transformer.h.28.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
178
+ "base_model.model.transformer.h.28.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
179
+ "base_model.model.transformer.h.28.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
180
+ "base_model.model.transformer.h.28.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
181
+ "base_model.model.transformer.h.28.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
182
+ "base_model.model.transformer.h.29.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
183
+ "base_model.model.transformer.h.29.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
184
+ "base_model.model.transformer.h.29.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
185
+ "base_model.model.transformer.h.29.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
186
+ "base_model.model.transformer.h.29.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
187
+ "base_model.model.transformer.h.29.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
188
+ "base_model.model.transformer.h.29.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
189
+ "base_model.model.transformer.h.29.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
190
+ "base_model.model.transformer.h.3.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
191
+ "base_model.model.transformer.h.3.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
192
+ "base_model.model.transformer.h.3.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
193
+ "base_model.model.transformer.h.3.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
194
+ "base_model.model.transformer.h.3.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
195
+ "base_model.model.transformer.h.3.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
196
+ "base_model.model.transformer.h.3.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
197
+ "base_model.model.transformer.h.3.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
198
+ "base_model.model.transformer.h.30.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
199
+ "base_model.model.transformer.h.30.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
200
+ "base_model.model.transformer.h.30.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
201
+ "base_model.model.transformer.h.30.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
202
+ "base_model.model.transformer.h.30.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
203
+ "base_model.model.transformer.h.30.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
204
+ "base_model.model.transformer.h.30.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
205
+ "base_model.model.transformer.h.30.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
206
+ "base_model.model.transformer.h.31.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
207
+ "base_model.model.transformer.h.31.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
208
+ "base_model.model.transformer.h.31.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
209
+ "base_model.model.transformer.h.31.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
210
+ "base_model.model.transformer.h.31.self_attention.dense.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
211
+ "base_model.model.transformer.h.31.self_attention.dense.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
212
+ "base_model.model.transformer.h.31.self_attention.query_key_value.lora_A.weight": "adapter_model-00003-of-00003.safetensors",
213
+ "base_model.model.transformer.h.31.self_attention.query_key_value.lora_B.weight": "adapter_model-00003-of-00003.safetensors",
214
+ "base_model.model.transformer.h.4.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
215
+ "base_model.model.transformer.h.4.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
216
+ "base_model.model.transformer.h.4.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
217
+ "base_model.model.transformer.h.4.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
218
+ "base_model.model.transformer.h.4.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
219
+ "base_model.model.transformer.h.4.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
220
+ "base_model.model.transformer.h.4.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
221
+ "base_model.model.transformer.h.4.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
222
+ "base_model.model.transformer.h.5.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
223
+ "base_model.model.transformer.h.5.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
224
+ "base_model.model.transformer.h.5.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
225
+ "base_model.model.transformer.h.5.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
226
+ "base_model.model.transformer.h.5.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
227
+ "base_model.model.transformer.h.5.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
228
+ "base_model.model.transformer.h.5.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
229
+ "base_model.model.transformer.h.5.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
230
+ "base_model.model.transformer.h.6.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
231
+ "base_model.model.transformer.h.6.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
232
+ "base_model.model.transformer.h.6.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
233
+ "base_model.model.transformer.h.6.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
234
+ "base_model.model.transformer.h.6.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
235
+ "base_model.model.transformer.h.6.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
236
+ "base_model.model.transformer.h.6.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
237
+ "base_model.model.transformer.h.6.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
238
+ "base_model.model.transformer.h.7.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
239
+ "base_model.model.transformer.h.7.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
240
+ "base_model.model.transformer.h.7.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
241
+ "base_model.model.transformer.h.7.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
242
+ "base_model.model.transformer.h.7.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
243
+ "base_model.model.transformer.h.7.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
244
+ "base_model.model.transformer.h.7.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
245
+ "base_model.model.transformer.h.7.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
246
+ "base_model.model.transformer.h.8.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
247
+ "base_model.model.transformer.h.8.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
248
+ "base_model.model.transformer.h.8.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
249
+ "base_model.model.transformer.h.8.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
250
+ "base_model.model.transformer.h.8.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
251
+ "base_model.model.transformer.h.8.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
252
+ "base_model.model.transformer.h.8.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
253
+ "base_model.model.transformer.h.8.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
254
+ "base_model.model.transformer.h.9.mlp.dense_4h_to_h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
255
+ "base_model.model.transformer.h.9.mlp.dense_4h_to_h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
256
+ "base_model.model.transformer.h.9.mlp.dense_h_to_4h.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
257
+ "base_model.model.transformer.h.9.mlp.dense_h_to_4h.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
258
+ "base_model.model.transformer.h.9.self_attention.dense.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
259
+ "base_model.model.transformer.h.9.self_attention.dense.lora_B.weight": "adapter_model-00001-of-00003.safetensors",
260
+ "base_model.model.transformer.h.9.self_attention.query_key_value.lora_A.weight": "adapter_model-00001-of-00003.safetensors",
261
+ "base_model.model.transformer.h.9.self_attention.query_key_value.lora_B.weight": "adapter_model-00001-of-00003.safetensors"
262
+ }
263
+ }