Hugging Face's logo

alicegoesdown
/
180c997e-93da-4a5f-b01f-a0fdd2cde362

PEFT
Safetensors
axolotl
Generated from Trainer
Model card Files Community
alicegoesdown commited on
Commit
3abc8ea
·
verified ·
1 Parent(s): 1a430b2

Training in progress, step 150

Browse files
Files changed (8) hide show
  1. adapter_config.json +108 -0
  2. adapter_model.safetensors +3 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +31 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
adapter_config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/opt-1.3b",
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": 0.2,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "model.decoder.layers.12.self_attn.out_proj",
24
+ "model.decoder.layers.22.self_attn.v_proj",
25
+ "model.decoder.layers.20.fc2",
26
+ "model.decoder.layers.2.fc2",
27
+ "model.decoder.layers.19.self_attn.v_proj",
28
+ "model.decoder.layers.4.fc1",
29
+ "model.decoder.layers.16.fc2",
30
+ "model.decoder.layers.5.self_attn.k_proj",
31
+ "model.decoder.layers.23.self_attn.v_proj",
32
+ "model.decoder.layers.1.self_attn.q_proj",
33
+ "model.decoder.layers.3.fc1",
34
+ "model.decoder.layers.21.self_attn.q_proj",
35
+ "model.decoder.layers.16.self_attn.q_proj",
36
+ "model.decoder.layers.19.fc2",
37
+ "model.decoder.layers.2.self_attn.v_proj",
38
+ "model.decoder.embed_tokens",
39
+ "model.decoder.layers.23.self_attn.out_proj",
40
+ "model.decoder.layers.3.fc2",
41
+ "model.decoder.layers.8.self_attn.v_proj",
42
+ "model.decoder.layers.13.fc1",
43
+ "model.decoder.layers.2.self_attn.k_proj",
44
+ "model.decoder.layers.4.self_attn.out_proj",
45
+ "model.decoder.layers.1.fc2",
46
+ "model.decoder.layers.14.fc2",
47
+ "model.decoder.layers.7.fc1",
48
+ "model.decoder.layers.17.fc1",
49
+ "model.decoder.layers.10.self_attn.q_proj",
50
+ "model.decoder.layers.22.self_attn.k_proj",
51
+ "model.decoder.layers.23.fc1",
52
+ "model.decoder.layers.9.self_attn.v_proj",
53
+ "model.decoder.layers.22.self_attn.q_proj",
54
+ "model.decoder.layers.23.fc2",
55
+ "model.decoder.embed_positions",
56
+ "model.decoder.layers.0.fc2",
57
+ "model.decoder.layers.0.fc1",
58
+ "model.decoder.layers.4.self_attn.k_proj",
59
+ "model.decoder.layers.20.self_attn.q_proj",
60
+ "model.decoder.layers.18.self_attn.k_proj",
61
+ "model.decoder.layers.5.fc2",
62
+ "model.decoder.layers.18.self_attn.q_proj",
63
+ "model.decoder.layers.12.self_attn.k_proj",
64
+ "model.decoder.layers.11.self_attn.k_proj",
65
+ "model.decoder.layers.1.self_attn.v_proj",
66
+ "model.decoder.layers.16.fc1",
67
+ "model.decoder.layers.6.self_attn.k_proj",
68
+ "model.decoder.layers.15.self_attn.out_proj",
69
+ "model.decoder.layers.23.self_attn.k_proj",
70
+ "model.decoder.layers.21.self_attn.v_proj",
71
+ "model.decoder.layers.9.self_attn.out_proj",
72
+ "model.decoder.layers.8.self_attn.out_proj",
73
+ "model.decoder.layers.19.self_attn.k_proj",
74
+ "model.decoder.layers.20.self_attn.out_proj",
75
+ "model.decoder.layers.7.self_attn.v_proj",
76
+ "model.decoder.layers.6.self_attn.v_proj",
77
+ "model.decoder.layers.22.fc2",
78
+ "model.decoder.layers.11.self_attn.q_proj",
79
+ "model.decoder.layers.13.fc2",
80
+ "model.decoder.layers.10.fc2",
81
+ "model.decoder.layers.8.self_attn.q_proj",
82
+ "model.decoder.layers.15.self_attn.k_proj",
83
+ "model.decoder.layers.0.self_attn.k_proj",
84
+ "model.decoder.layers.17.self_attn.k_proj",
85
+ "model.decoder.layers.3.self_attn.k_proj",
86
+ "model.decoder.layers.13.self_attn.q_proj",
87
+ "model.decoder.layers.9.self_attn.k_proj",
88
+ "model.decoder.layers.14.self_attn.k_proj",
89
+ "model.decoder.layers.23.self_attn.q_proj",
90
+ "model.decoder.layers.15.self_attn.q_proj",
91
+ "model.decoder.layers.22.fc1",
92
+ "model.decoder.layers.18.self_attn.v_proj",
93
+ "model.decoder.layers.12.fc2",
94
+ "model.decoder.layers.5.self_attn.v_proj",
95
+ "model.decoder.layers.7.self_attn.out_proj",
96
+ "model.decoder.layers.21.fc2",
97
+ "model.decoder.layers.6.fc1",
98
+ "model.decoder.layers.10.self_attn.v_proj",
99
+ "model.decoder.layers.22.self_attn.out_proj",
100
+ "lm_head",
101
+ "model.decoder.layers.14.self_attn.out_proj",
102
+ "model.decoder.layers.17.self_attn.v_proj",
103
+ "model.decoder.layers.11.self_attn.v_proj"
104
+ ],
105
+ "task_type": "CAUSAL_LM",
106
+ "use_dora": false,
107
+ "use_rslora": false
108
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0a9a11c1b9ce6985dcb84c056416f9e8b85735afb65813cbc1b759635aa01d
3
+ size 972626912
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "extra_special_tokens": {},
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abf0f2b89238f81036c58be60fc1eedc2b143f00d1d6d91ce22308e5948e117
3
+ size 5368
vocab.json ADDED
The diff for this file is too large to render. See raw diff