Hugging Face's logo

alicegoesdown
/
bf548f21-5e2e-4b0c-84e9-2e26778f24db

PEFT
Safetensors
axolotl
Generated from Trainer
Model card Files Community
alicegoesdown commited on
Commit
14ca918
·
verified ·
1 Parent(s): 730f918

Training in progress, step 150

Browse files
Files changed (7) hide show
  1. adapter_config.json +164 -0
  2. adapter_model.safetensors +3 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer.json +0 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +42 -0
  7. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.3,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 64,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "model.layers.0.mlp.up_proj",
26
+ "model.layers.14.mlp.gate_proj",
27
+ "model.layers.2.mlp.up_proj",
28
+ "model.layers.5.mlp.gate_proj",
29
+ "model.layers.18.self_attn.k_proj",
30
+ "model.layers.11.mlp.gate_proj",
31
+ "model.layers.18.self_attn.v_proj",
32
+ "model.layers.16.self_attn.q_proj",
33
+ "model.layers.4.mlp.up_proj",
34
+ "model.layers.18.mlp.up_proj",
35
+ "model.layers.23.self_attn.v_proj",
36
+ "model.layers.3.mlp.down_proj",
37
+ "model.layers.31.mlp.gate_proj",
38
+ "model.layers.20.mlp.down_proj",
39
+ "model.layers.12.mlp.up_proj",
40
+ "model.layers.21.self_attn.o_proj",
41
+ "model.layers.20.self_attn.k_proj",
42
+ "model.layers.7.self_attn.o_proj",
43
+ "model.layers.4.mlp.down_proj",
44
+ "model.layers.12.self_attn.o_proj",
45
+ "model.layers.3.mlp.gate_proj",
46
+ "model.embed_tokens",
47
+ "model.layers.8.mlp.gate_proj",
48
+ "model.layers.22.self_attn.k_proj",
49
+ "model.layers.21.self_attn.k_proj",
50
+ "model.layers.3.self_attn.o_proj",
51
+ "model.layers.8.self_attn.k_proj",
52
+ "model.layers.12.self_attn.q_proj",
53
+ "model.layers.9.self_attn.q_proj",
54
+ "model.layers.20.mlp.gate_proj",
55
+ "model.layers.30.self_attn.k_proj",
56
+ "model.layers.16.self_attn.k_proj",
57
+ "model.layers.31.self_attn.o_proj",
58
+ "model.layers.25.mlp.gate_proj",
59
+ "model.layers.19.mlp.down_proj",
60
+ "model.layers.29.self_attn.v_proj",
61
+ "model.layers.28.mlp.up_proj",
62
+ "model.layers.23.mlp.down_proj",
63
+ "model.layers.27.mlp.gate_proj",
64
+ "model.layers.11.self_attn.q_proj",
65
+ "model.layers.26.self_attn.o_proj",
66
+ "model.layers.27.self_attn.v_proj",
67
+ "model.layers.8.mlp.down_proj",
68
+ "model.layers.29.self_attn.k_proj",
69
+ "model.layers.14.self_attn.q_proj",
70
+ "model.layers.19.mlp.up_proj",
71
+ "model.layers.0.mlp.down_proj",
72
+ "model.layers.13.mlp.down_proj",
73
+ "model.layers.25.self_attn.o_proj",
74
+ "model.layers.15.self_attn.q_proj",
75
+ "model.layers.24.self_attn.v_proj",
76
+ "model.layers.29.mlp.up_proj",
77
+ "model.layers.26.self_attn.k_proj",
78
+ "model.layers.17.self_attn.v_proj",
79
+ "model.layers.18.mlp.down_proj",
80
+ "model.layers.25.mlp.up_proj",
81
+ "model.layers.3.self_attn.q_proj",
82
+ "model.layers.5.self_attn.k_proj",
83
+ "model.layers.31.self_attn.k_proj",
84
+ "model.layers.6.self_attn.k_proj",
85
+ "model.layers.9.self_attn.v_proj",
86
+ "model.layers.16.self_attn.o_proj",
87
+ "model.layers.17.self_attn.o_proj",
88
+ "model.layers.30.self_attn.o_proj",
89
+ "model.layers.5.mlp.down_proj",
90
+ "model.layers.31.self_attn.v_proj",
91
+ "model.layers.16.mlp.down_proj",
92
+ "model.layers.8.self_attn.v_proj",
93
+ "model.layers.10.mlp.gate_proj",
94
+ "model.layers.28.mlp.down_proj",
95
+ "model.layers.4.self_attn.k_proj",
96
+ "model.layers.4.self_attn.q_proj",
97
+ "model.layers.7.self_attn.k_proj",
98
+ "model.layers.27.mlp.down_proj",
99
+ "model.layers.28.mlp.gate_proj",
100
+ "model.layers.31.self_attn.q_proj",
101
+ "model.layers.30.mlp.gate_proj",
102
+ "model.layers.13.mlp.up_proj",
103
+ "model.layers.23.self_attn.o_proj",
104
+ "model.layers.25.self_attn.k_proj",
105
+ "model.layers.12.mlp.gate_proj",
106
+ "model.layers.30.mlp.down_proj",
107
+ "model.layers.30.self_attn.q_proj",
108
+ "model.layers.13.mlp.gate_proj",
109
+ "model.layers.6.self_attn.v_proj",
110
+ "model.layers.29.self_attn.o_proj",
111
+ "model.layers.27.self_attn.k_proj",
112
+ "model.layers.1.mlp.down_proj",
113
+ "model.layers.22.self_attn.v_proj",
114
+ "model.layers.26.mlp.up_proj",
115
+ "model.layers.10.self_attn.v_proj",
116
+ "model.layers.2.mlp.down_proj",
117
+ "model.layers.9.mlp.gate_proj",
118
+ "model.layers.28.self_attn.o_proj",
119
+ "model.layers.1.self_attn.q_proj",
120
+ "model.layers.13.self_attn.v_proj",
121
+ "model.layers.14.mlp.down_proj",
122
+ "model.layers.20.mlp.up_proj",
123
+ "model.layers.17.mlp.down_proj",
124
+ "model.layers.11.self_attn.v_proj",
125
+ "model.layers.7.mlp.down_proj",
126
+ "model.layers.10.self_attn.q_proj",
127
+ "model.layers.15.self_attn.k_proj",
128
+ "model.layers.2.mlp.gate_proj",
129
+ "model.layers.6.mlp.gate_proj",
130
+ "model.layers.30.self_attn.v_proj",
131
+ "model.layers.15.self_attn.v_proj",
132
+ "model.layers.23.self_attn.q_proj",
133
+ "model.layers.22.mlp.up_proj",
134
+ "model.layers.31.mlp.up_proj",
135
+ "model.layers.31.mlp.down_proj",
136
+ "model.layers.7.self_attn.q_proj",
137
+ "model.layers.9.mlp.down_proj",
138
+ "model.layers.24.mlp.down_proj",
139
+ "model.layers.17.self_attn.k_proj",
140
+ "model.layers.0.self_attn.q_proj",
141
+ "model.layers.14.self_attn.k_proj",
142
+ "model.layers.24.self_attn.k_proj",
143
+ "model.layers.5.self_attn.o_proj",
144
+ "model.layers.6.self_attn.o_proj",
145
+ "model.layers.26.self_attn.v_proj",
146
+ "model.layers.21.self_attn.v_proj",
147
+ "model.layers.19.self_attn.q_proj",
148
+ "model.layers.1.self_attn.k_proj",
149
+ "model.layers.21.mlp.down_proj",
150
+ "model.layers.24.self_attn.q_proj",
151
+ "model.layers.10.self_attn.o_proj",
152
+ "model.layers.0.self_attn.v_proj",
153
+ "model.layers.11.self_attn.o_proj",
154
+ "model.layers.19.self_attn.k_proj",
155
+ "model.layers.1.mlp.up_proj",
156
+ "model.layers.22.self_attn.q_proj",
157
+ "model.layers.2.self_attn.q_proj",
158
+ "model.layers.15.mlp.up_proj",
159
+ "model.layers.30.mlp.up_proj"
160
+ ],
161
+ "task_type": "CAUSAL_LM",
162
+ "use_dora": false,
163
+ "use_rslora": true
164
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2358799f680e1b5bc27a7f6629fdf4de5ec71757c7cb2b3d7c3bb3837d965b
3
+ size 653434568
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a23cf9d7593da5923809910b69bd7365e1e89227ae799463428f3c2a35c945e
3
+ size 5496