akrishnan commited on
Commit
6fc159d
1 Parent(s): e47d4c9

Training in progress, step 1250

Browse files
cfg.yaml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model_family: olmo-7b
2
+ LoRA:
3
+ r: 0
4
+ alpha: 32
5
+ dropout: 0.05
6
+ data_path: locuslab/TOFU
7
+ split: full
8
+ batch_size: 8
9
+ gradient_accumulation_steps: 4
10
+ num_epochs: 10
11
+ lr: 9.0e-06
12
+ seed: 42
13
+ run_index: 1
14
+ save_dir: paper_models/final_ft_noLORA_${num_epochs}_epochs_inst_lr${lr}_${model_family}_${split}_seed${seed}_${run_index}/
15
+ weight_decay: 0.01
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/OLMo-7B-0724-Instruct-hf",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": null,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.45.2",
26
+ "use_cache": false,
27
+ "vocab_size": 50304
28
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f603505a5b9d7ed1b449f9b1e0e8817c04fb40640e4ab3e1ec78abd8d23f53c5
3
+ size 4998571312
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c9daa767e1cd1034f8be1db1c08574e1936180573f718525099f6635a627ce
3
+ size 4947191504
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba129de01d50d1218b94d424ec192e3a1061fc8b63e3bc4588d50a8f5f88ecf
3
+ size 3830455008
model.safetensors.index.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13776191488
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
94
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
95
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
96
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
97
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
98
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
121
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
123
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
128
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
130
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
131
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
132
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
133
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
171
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
174
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
175
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
176
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
191
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
192
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
193
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
194
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
195
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
196
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
232
+ }
233
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100f1a84773f7fb85d5f68b501a1fce5fd8b903f600a27a2c028baa1c792f366
3
+ size 5368