Hugging Face's logo

alicegoesdown
/
testypoos2

Safetensors
Model card Files
xet
Community
alicegoesdown commited on
Commit
d834376
·
verified ·
1 Parent(s): 584c56b

Training in progress, step 150

Browse files
Files changed (7) hide show
  1. adapter_config.json +140 -9
  2. adapter_model.safetensors +2 -2
  3. special_tokens_map.json +1 -1
  4. tokenizer.json +2 -2
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +9 -13
  7. training_args.bin +2 -2
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "bigscience/bloomz-560m",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -14,20 +14,151 @@
14
  "lora_dropout": 0.3,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
- "modules_to_save": null,
 
 
18
  "peft_type": "LORA",
19
  "r": 4,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "dense",
24
- "query_key_value",
25
- "lm_head",
26
- "word_embeddings",
27
- "dense_4h_to_h",
28
- "dense_h_to_4h"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
32
- "use_rslora": false
33
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-v0.2-bnb-4bit",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
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": 4,
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
+ "model.layers.27.self_attn.v_proj",
26
+ "model.layers.28.mlp.down_proj",
27
+ "model.layers.12.self_attn.q_proj",
28
+ "model.layers.28.self_attn.o_proj",
29
+ "model.layers.9.self_attn.v_proj",
30
+ "model.layers.14.self_attn.q_proj",
31
+ "model.layers.19.self_attn.q_proj",
32
+ "model.layers.27.mlp.gate_proj",
33
+ "model.layers.17.self_attn.o_proj",
34
+ "model.layers.23.self_attn.o_proj",
35
+ "model.layers.22.self_attn.v_proj",
36
+ "model.layers.25.self_attn.o_proj",
37
+ "model.layers.0.mlp.down_proj",
38
+ "model.layers.20.mlp.gate_proj",
39
+ "model.layers.9.mlp.gate_proj",
40
+ "model.layers.18.self_attn.k_proj",
41
+ "model.layers.21.self_attn.k_proj",
42
+ "model.layers.17.self_attn.k_proj",
43
+ "model.layers.3.self_attn.q_proj",
44
+ "model.layers.24.self_attn.q_proj",
45
+ "model.layers.26.mlp.up_proj",
46
+ "model.layers.31.mlp.up_proj",
47
+ "model.layers.1.mlp.down_proj",
48
+ "model.layers.13.mlp.up_proj",
49
+ "model.layers.5.mlp.down_proj",
50
+ "model.layers.3.self_attn.o_proj",
51
+ "model.layers.29.self_attn.k_proj",
52
+ "model.layers.3.mlp.down_proj",
53
+ "model.layers.20.mlp.down_proj",
54
+ "model.layers.2.mlp.gate_proj",
55
+ "model.layers.16.self_attn.q_proj",
56
+ "model.layers.14.mlp.down_proj",
57
+ "model.layers.6.self_attn.o_proj",
58
+ "model.layers.26.self_attn.o_proj",
59
+ "model.layers.6.self_attn.k_proj",
60
+ "model.layers.21.mlp.down_proj",
61
+ "model.layers.9.mlp.down_proj",
62
+ "model.layers.31.self_attn.o_proj",
63
+ "model.layers.7.self_attn.k_proj",
64
+ "model.layers.12.self_attn.o_proj",
65
+ "model.layers.14.mlp.gate_proj",
66
+ "model.layers.8.mlp.down_proj",
67
+ "model.layers.16.self_attn.o_proj",
68
+ "model.layers.15.self_attn.k_proj",
69
+ "model.layers.21.self_attn.o_proj",
70
+ "model.layers.13.self_attn.v_proj",
71
+ "model.layers.7.mlp.down_proj",
72
+ "model.layers.21.self_attn.v_proj",
73
+ "model.layers.27.self_attn.k_proj",
74
+ "model.layers.18.self_attn.v_proj",
75
+ "model.layers.15.self_attn.q_proj",
76
+ "model.layers.1.self_attn.k_proj",
77
+ "model.layers.5.mlp.gate_proj",
78
+ "model.layers.2.self_attn.q_proj",
79
+ "model.layers.28.mlp.up_proj",
80
+ "model.layers.10.mlp.gate_proj",
81
+ "model.layers.29.mlp.up_proj",
82
+ "model.layers.7.self_attn.q_proj",
83
+ "model.layers.12.mlp.gate_proj",
84
+ "model.layers.20.mlp.up_proj",
85
+ "model.layers.4.mlp.up_proj",
86
+ "model.layers.23.self_attn.q_proj",
87
+ "model.layers.23.self_attn.v_proj",
88
+ "model.layers.1.self_attn.q_proj",
89
+ "model.layers.27.mlp.down_proj",
90
+ "model.layers.30.mlp.down_proj",
91
+ "model.layers.17.mlp.down_proj",
92
+ "model.layers.25.mlp.up_proj",
93
+ "model.layers.4.self_attn.k_proj",
94
+ "model.layers.2.mlp.up_proj",
95
+ "model.layers.6.mlp.gate_proj",
96
+ "model.layers.31.self_attn.v_proj",
97
+ "model.layers.30.self_attn.k_proj",
98
+ "model.layers.30.self_attn.q_proj",
99
+ "model.layers.30.mlp.gate_proj",
100
+ "model.layers.8.mlp.gate_proj",
101
+ "model.layers.13.mlp.down_proj",
102
+ "model.layers.10.self_attn.q_proj",
103
+ "model.layers.22.self_attn.q_proj",
104
+ "model.layers.15.self_attn.v_proj",
105
+ "model.layers.25.mlp.gate_proj",
106
+ "model.layers.4.self_attn.q_proj",
107
+ "model.embed_tokens",
108
+ "model.layers.14.self_attn.k_proj",
109
+ "model.layers.31.mlp.down_proj",
110
+ "model.layers.31.self_attn.q_proj",
111
+ "model.layers.1.mlp.up_proj",
112
+ "model.layers.2.mlp.down_proj",
113
+ "model.layers.12.mlp.up_proj",
114
+ "model.layers.19.mlp.up_proj",
115
+ "model.layers.0.self_attn.v_proj",
116
+ "model.layers.8.self_attn.v_proj",
117
+ "model.layers.5.self_attn.o_proj",
118
+ "model.layers.11.mlp.gate_proj",
119
+ "model.layers.18.mlp.up_proj",
120
+ "model.layers.10.self_attn.v_proj",
121
+ "model.layers.23.mlp.down_proj",
122
+ "model.layers.0.mlp.up_proj",
123
+ "model.layers.8.self_attn.k_proj",
124
+ "model.layers.13.mlp.gate_proj",
125
+ "model.layers.24.self_attn.k_proj",
126
+ "model.layers.24.mlp.down_proj",
127
+ "model.layers.15.mlp.up_proj",
128
+ "model.layers.25.self_attn.k_proj",
129
+ "model.layers.6.self_attn.v_proj",
130
+ "model.layers.29.self_attn.o_proj",
131
+ "model.layers.10.self_attn.o_proj",
132
+ "model.layers.31.mlp.gate_proj",
133
+ "model.layers.30.mlp.up_proj",
134
+ "model.layers.16.mlp.down_proj",
135
+ "model.layers.30.self_attn.o_proj",
136
+ "model.layers.7.self_attn.o_proj",
137
+ "model.layers.5.self_attn.k_proj",
138
+ "model.layers.0.self_attn.q_proj",
139
+ "model.layers.16.self_attn.k_proj",
140
+ "model.layers.19.mlp.down_proj",
141
+ "model.layers.17.self_attn.v_proj",
142
+ "model.layers.29.self_attn.v_proj",
143
+ "model.layers.9.self_attn.q_proj",
144
+ "model.layers.26.self_attn.k_proj",
145
+ "model.layers.11.self_attn.q_proj",
146
+ "model.layers.24.self_attn.v_proj",
147
+ "model.layers.18.mlp.down_proj",
148
+ "model.layers.11.self_attn.v_proj",
149
+ "model.layers.19.self_attn.k_proj",
150
+ "model.layers.26.self_attn.v_proj",
151
+ "model.layers.28.mlp.gate_proj",
152
+ "model.layers.22.self_attn.k_proj",
153
+ "model.layers.31.self_attn.k_proj",
154
+ "model.layers.3.mlp.gate_proj",
155
+ "model.layers.22.mlp.up_proj",
156
+ "model.layers.30.self_attn.v_proj",
157
+ "model.layers.4.mlp.down_proj",
158
+ "model.layers.20.self_attn.k_proj",
159
+ "model.layers.11.self_attn.o_proj"
160
  ],
161
  "task_type": "CAUSAL_LM",
162
  "use_dora": false,
163
+ "use_rslora": true
164
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55c0a593ed281b8f8c6aaa03a3b05a443edb079f9e732f4ac5c120a396d6d8e3
3
- size 2069589712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a0ef7164d47257fa5e03e94a378e8b160912c89dea19a8e1f7af4d4f485094
3
+ size 287644488
special_tokens_map.json CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<pad>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<unk>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
3
- size 21763085
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2699839c243202a04a90537576fc719283f638e90fe80feb469888275289575
3
+ size 3505751
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json CHANGED
@@ -1,5 +1,7 @@
1
  {
2
- "add_prefix_space": false,
 
 
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<unk>",
@@ -24,25 +26,19 @@
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
- },
28
- "3": {
29
- "content": "<pad>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
  }
36
  },
37
  "bos_token": "<s>",
38
  "clean_up_tokenization_spaces": false,
39
  "eos_token": "</s>",
40
  "extra_special_tokens": {},
41
- "merges_file": null,
42
  "model_max_length": 1000000000000000019884624838656,
43
- "pad_token": "<pad>",
44
  "padding_side": "left",
45
- "tokenizer_class": "BloomTokenizer",
 
 
46
  "unk_token": "<unk>",
47
- "vocab_file": null
48
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
 
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": "<unk>",
38
  "padding_side": "left",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
  "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87daafd6e0abf7887fe4ba7916c751fc99e13e4a39fb4df26920bf9257b8000d
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bdf1390d17124cf4f93eac9a9298192534d0bd0ab8b33fa14cac1a258bda108
3
+ size 5496