Hugging Face's logo

bgglee
/
NL2SQL_finetuned

Safetensors
llama
Model card Files
xet
Community
bgglee commited on
Commit
d34ba01
·
1 Parent(s): 1719518

Upload final model (dense_save) + logs + config

Browse files
Files changed (10) hide show
  1. README.md +18 -12
  2. finetune_config.json +13 -9
  3. model-00001-of-00002.safetensors +2 -2
  4. model-00002-of-00002.safetensors +2 -2
  5. model.safetensors.index.json +338 -114
  6. repair_logs.json +47 -0
  7. tokenizer.json +2 -2
  8. training_loss.csv +9 -12
  9. training_loss.png +0 -0
  10. wrong_ids.json +7 -1
README.md CHANGED
@@ -1,17 +1,23 @@
1
- # NL2SQL Fine-Tuned Model v3
2
- This is an updated version with self-correction and improved hyperparameters.
 
 
3
 
4
- ## Config
5
  {
6
- "version": "v3",
7
  "base_model": "./hf_models/meta-llama--Llama-3.2-3B-Instruct",
8
- "merged_repo": "bgglee/NL2SQL_finetuned",
9
- "method": "LoRA (merged)",
10
- "learning_rate": 0.0001,
11
- "epochs": 2,
 
12
  "batch_size": 2,
13
- "grad_accum": 4,
14
- "warmup_ratio": 0.05,
15
- "weight_decay": 0.01,
16
- "max_len": 1024
 
 
 
 
17
  }
 
1
+ # NL2SQL Fine-Tuned Model (Full Merged or Dense)
2
+ - Base: ./hf_models/meta-llama--Llama-3.2-3B-Instruct
3
+ - Merge route: dense_save
4
+ It has been saved to be directly loadable by `AutoModelForCausalLM.from_pretrained(...)`.
5
 
6
+ ## Training Config
7
  {
 
8
  "base_model": "./hf_models/meta-llama--Llama-3.2-3B-Instruct",
9
+ "merged_model_repo": "bgglee/NL2SQL_finetuned",
10
+ "method": "Dense FT",
11
+ "merge_route": "dense_save",
12
+ "learning_rate": 0.0002,
13
+ "epochs": 1.0,
14
  "batch_size": 2,
15
+ "grad_accum": 8,
16
+ "lora_r": 16,
17
+ "lora_alpha": 16,
18
+ "lora_dropout": 0.05,
19
+ "max_len": 768,
20
+ "max_new_tokens_gen": 150,
21
+ "dataset": "data/bird/BIRD_train_1434ea.json",
22
+ "schema_dir": "data/bird/BIRD_SQLite"
23
  }
finetune_config.json CHANGED
@@ -1,13 +1,17 @@
1
  {
2
- "version": "v3",
3
  "base_model": "./hf_models/meta-llama--Llama-3.2-3B-Instruct",
4
- "merged_repo": "bgglee/NL2SQL_finetuned",
5
- "method": "LoRA (merged)",
6
- "learning_rate": 0.0001,
7
- "epochs": 2,
 
8
  "batch_size": 2,
9
- "grad_accum": 4,
10
- "warmup_ratio": 0.05,
11
- "weight_decay": 0.01,
12
- "max_len": 1024
 
 
 
 
13
  }
 
1
  {
 
2
  "base_model": "./hf_models/meta-llama--Llama-3.2-3B-Instruct",
3
+ "merged_model_repo": "bgglee/NL2SQL_finetuned",
4
+ "method": "Dense FT",
5
+ "merge_route": "dense_save",
6
+ "learning_rate": 0.0002,
7
+ "epochs": 1.0,
8
  "batch_size": 2,
9
+ "grad_accum": 8,
10
+ "lora_r": 16,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "max_len": 768,
14
+ "max_new_tokens_gen": 150,
15
+ "dataset": "data/bird/BIRD_train_1434ea.json",
16
+ "schema_dir": "data/bird/BIRD_SQLite"
17
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:327be157f17b9c75f03b065000ad4decd2e8627dfb2873a44c582969a63377a5
3
- size 4965799096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615e8e9abd3e3d3d2258b266d3c4b48cf833184c29a2510fea9b40c0ff629356
3
+ size 4993346104
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a25a2554bc877ae6efdd628c84985539c5b1542870310551a44427a6abd9448b
3
- size 1459729952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608d88b0e7bc8c00f659e23eb1f215feba71aaeb43044ee35686b5ba071dfb5e
3
+ size 1468912240
model.safetensors.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
- "total_parameters": 3212749824,
4
- "total_size": 6425499648
5
  },
6
  "weight_map": {
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -10,253 +10,477 @@
10
  "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
  "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
  "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
17
  "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
  "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
  "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
  "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
26
  "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
  "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
  "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
  "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
  "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
35
  "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
  "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
  "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
  "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
  "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
44
  "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
  "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
  "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
  "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
  "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
53
  "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
  "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
  "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
  "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
  "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
62
  "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
  "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
  "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
  "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
  "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
71
  "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
  "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
  "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
  "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
  "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
80
  "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
  "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
  "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
  "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
  "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
89
  "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
  "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
  "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
  "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
  "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
98
  "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
  "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
  "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
  "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
  "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
107
  "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
  "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
  "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
  "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
  "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
116
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
  "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
  "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
  "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
  "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
125
  "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
  "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
  "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
  "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
  "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
134
  "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
  "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
  "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
  "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
  "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
143
  "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
  "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
  "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
  "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
  "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
152
  "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
  "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
  "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
  "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
  "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
161
  "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
  "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
  "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
  "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
  "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
170
  "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
  "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
  "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
  "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
  "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
179
  "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
  "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
  "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
  "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
  "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
188
  "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
  "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
  "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
  "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
  "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
 
 
 
 
 
 
 
 
197
  "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
  "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
  "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
  "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
  "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
206
  "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
  "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
  "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
  "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
  "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
215
  "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
  "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
  "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
  "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
  "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
224
  "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
  "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
  "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
  "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
  "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
233
  "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
  "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
  "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
  "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
  "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
242
  "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
  "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
  "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
  "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
  "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
251
  "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
  "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
  "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
  "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
  "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
 
 
 
 
 
 
 
 
260
  "model.norm.weight": "model-00002-of-00002.safetensors"
261
  }
262
  }
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 3221924864,
4
+ "total_size": 6462199808
5
  },
6
  "weight_map": {
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
 
10
  "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
  "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
  "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
25
  "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
  "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
  "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
  "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
42
  "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
43
  "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
44
  "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
  "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
  "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
59
  "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
60
  "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
61
  "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
62
  "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
63
  "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
76
  "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
77
  "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
78
  "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
79
  "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
80
  "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
93
  "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
  "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
  "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
  "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
  "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
110
  "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
  "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
112
  "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
113
  "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
114
  "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
127
  "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
  "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
  "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
  "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
  "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
144
  "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
145
  "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
146
  "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
147
  "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
148
  "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
161
  "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
  "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
  "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
  "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
  "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
178
  "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
  "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
180
  "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
181
  "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
182
  "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.18.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
195
  "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
  "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
197
  "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
198
  "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
199
  "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.19.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
212
  "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
213
  "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
214
  "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
215
  "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
216
  "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
229
  "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
  "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
  "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
232
  "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
233
  "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.20.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
246
  "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
247
  "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
248
  "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
249
  "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
250
  "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
263
  "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
264
  "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
265
  "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
266
  "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
267
  "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.22.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
280
  "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
281
  "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
282
  "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
283
  "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
284
  "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.23.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
297
  "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
298
  "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
299
  "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
300
  "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
301
  "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.24.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
314
  "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
315
  "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
316
  "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
317
  "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
318
  "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.25.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
331
  "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
  "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
  "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
  "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
  "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.26.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
348
  "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
  "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
350
  "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
351
  "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
352
  "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.27.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
365
  "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
366
  "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
367
  "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
368
  "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
369
  "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
382
  "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
  "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
  "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
  "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
  "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
399
  "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
400
  "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
401
  "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
402
  "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
403
  "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
416
  "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
  "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
  "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
  "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
  "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
433
  "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
434
  "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
435
  "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
436
  "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
437
  "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
450
  "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
451
  "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
452
  "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
453
  "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
454
  "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
467
  "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
468
  "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
469
  "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
470
  "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
471
  "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
472
+ "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
484
  "model.norm.weight": "model-00002-of-00002.safetensors"
485
  }
486
  }
repair_logs.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "qid": 98,
4
+ "db_id": "financial",
5
+ "pred_sql": "SELECT T1.account_id FROM account AS T1 INNER JOIN loan AS T2 ON T1.account_id = T2.account_id WHERE STRFTIME('%Y', T2.date) = '1997' ORDER BY T2.amount ASC LIMIT 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,",
6
+ "err": "EXEC_ERR: near \",\": syntax error",
7
+ "repaired_sql": "SELECT T1.account_id FROM account AS T1 INNER JOIN loan AS T2 ON T1.account_id = T2.account_id WHERE STRFTIME('%Y', T2.date) = '1997' ORDER BY T2.amount ASC LIMIT 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n\n### ERROR ###\nEXEC_ERR: near \",\": syntax error\n\n### SCHEMA ###\nCREATE TABLE account (\n account_id INTEGER,\n district_id INTEGER,\n frequency TEXT,\n date DATE,\n FOREIGN KEY(district_id) REFERENCES district(district_id)\n)",
8
+ "repair_ok": false,
9
+ "repair_err": "EXEC_ERR: near \",\": syntax error"
10
+ },
11
+ {
12
+ "qid": 596,
13
+ "db_id": "codebase_community",
14
+ "pred_sql": "SELECT T1.DisplayName, T2.Name FROM users AS T1 INNER JOIN badges AS T2 ON T1.Id = T2.UserId ORDER BY T2.Id DESC LIMIT 1",
15
+ "err": "MISMATCH",
16
+ "repaired_sql": "SELECT T1.DisplayName, T2.Name FROM users AS T1 INNER JOIN badges AS T2 ON T1.Id = T2.UserId ORDER BY T2.Id DESC LIMIT 1\n\n### ERROR ###\nMISMATCH\n\n### SCHEMA ###\nCREATE TABLE badges (\n Id INTEGER,\n UserId INTEGER,\n Name TEXT,\n Date DATETIME,\n FOREIGN KEY(UserId) REFERENCES users(Id)\n)",
17
+ "repair_ok": false,
18
+ "repair_err": "EXEC_ERR: unrecognized token: \"#\""
19
+ },
20
+ {
21
+ "qid": 444,
22
+ "db_id": "card_games",
23
+ "pred_sql": "SELECT T1.name, T1.type FROM foreign_data AS T1 INNER JOIN cards AS T2 ON T1.uuid = T2.uuid WHERE T2.watermark = 'Boros' AND T2.type = 'Card' AND T1.type = 'Foreign' AND T1.name IS NOT NULL AND T1.name!= '' AND T1.name!='' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T",
24
+ "err": "EXEC_ERR: no such column: T",
25
+ "repaired_sql": "SELECT T1.name, T1.type FROM foreign_data AS T1 INNER JOIN cards AS T2 ON T1.uuid = T2.uuid WHERE T2.watermark = 'Boros' AND T2.type = 'Card' AND T1.type = 'Foreign' AND T1.name IS NOT NULL AND T1.name!= '' AND T1.name!='' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T1.name!= 'Unknown' AND T1.name!= 'None' AND T\n\n### ERROR ###\nEXEC_ERR: no such column: T\n\n### SCHEMA ###\nCREATE TABLE sqlite_sequence (\n name TEXT,\n seq TEXT\n)",
26
+ "repair_ok": false,
27
+ "repair_err": "EXEC_ERR: unrecognized token: \"#\""
28
+ },
29
+ {
30
+ "qid": 999,
31
+ "db_id": "formula_1",
32
+ "pred_sql": "SELECT T2.name FROM results AS T1 INNER JOIN races AS T2 ON T1.raceId = T2.raceId ORDER BY T1.fastestLapTime LIMIT 1",
33
+ "err": "MISMATCH",
34
+ "repaired_sql": "SELECT T2.name FROM results AS T1 INNER JOIN races AS T2 ON T1.raceId = T2.raceId ORDER BY T1.fastestLapTime LIMIT 1\n\n### ERROR ###\nMISMATCH\n\n### SCHEMA ###\nCREATE TABLE sqlite_sequence (\n name TEXT,\n seq TEXT\n)",
35
+ "repair_ok": false,
36
+ "repair_err": "EXEC_ERR: unrecognized token: \"#\""
37
+ },
38
+ {
39
+ "qid": 321,
40
+ "db_id": "toxicology",
41
+ "pred_sql": "SELECT T1.molecule_id, T2.molecule_id FROM atom AS T1 INNER JOIN connected AS T2 ON T1.atom_id = T2.atom_id WHERE T1.atom_id = 'TR000_2' AND T2.atom_id = 'TR000_4' AND T1.molecule_id = T2.molecule_id",
42
+ "err": "EXEC_ERR: no such column: T2.molecule_id",
43
+ "repaired_sql": "SELECT T1.molecule_id, T2.molecule_id FROM atom AS T1 INNER JOIN connected AS T2 ON T1.atom_id = T2.atom_id WHERE T1.atom_id = 'TR000_2' AND T2.atom_id = 'TR000_4' AND T1.molecule_id = T2.molecule_id\n\n### ERROR ###\nEXEC_ERR: no such column: T2.molecule_id\n\n### SCHEMA ###\nCREATE TABLE atom (\n atom_id TEXT,\n molecule_id TEXT,\n element TEXT,\n FOREIGN KEY(molecule_id) REFERENCES molecule(molecule_id)\n)",
44
+ "repair_ok": false,
45
+ "repair_err": "EXEC_ERR: unrecognized token: \"#\""
46
+ }
47
+ ]
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
3
- size 17210019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
training_loss.csv CHANGED
@@ -1,13 +1,10 @@
1
  step,loss
2
- 10,0.0329
3
- 20,0.0293
4
- 30,0.0239
5
- 40,0.0236
6
- 50,0.0187
7
- 60,0.0224
8
- 70,0.0248
9
- 80,0.0261
10
- 90,0.0212
11
- 100,0.0233
12
- 110,0.0159
13
- 120,0.0228
 
1
  step,loss
2
+ 10,0.2984
3
+ 20,0.1834
4
+ 30,0.1896
5
+ 40,0.1749
6
+ 50,0.1857
7
+ 60,0.1904
8
+ 70,0.1948
9
+ 80,0.1857
10
+ 90,0.2007
 
 
 
training_loss.png CHANGED
wrong_ids.json CHANGED
@@ -1 +1,7 @@
1
- []
 
 
 
 
 
 
 
1
+ [
2
+ 98,
3
+ 596,
4
+ 444,
5
+ 999,
6
+ 321
7
+ ]