sam2ai commited on
Commit
5af0d78
1 Parent(s): 195ab66

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,21 @@
1
  ---
2
- license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
  ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "facebook/xglm-564M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 128,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "fc1",
18
+ "fc2",
19
+ "q_proj",
20
+ "v_proj",
21
+ "k_proj",
22
+ "out_proj"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67c574f6ccf2d15d6667deca19c7effb941cc573a5d4643af77e2a8e1960a4e
3
+ size 226595405
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<madeupword0>": 256001,
4
+ "<madeupword1>": 256002,
5
+ "<madeupword2>": 256003,
6
+ "<madeupword3>": 256004,
7
+ "<madeupword4>": 256005,
8
+ "<madeupword5>": 256006,
9
+ "<madeupword6>": 256007,
10
+ "<pad>": 1,
11
+ "<s>": 0,
12
+ "<unk>": 3
13
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xglm-564M",
3
+ "activation_dropout": 0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "XGLMForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "attention_heads": 16,
10
+ "bos_token_id": 0,
11
+ "d_model": 1024,
12
+ "decoder_start_token_id": 2,
13
+ "dropout": 0.1,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 4096,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "xglm",
20
+ "num_layers": 24,
21
+ "pad_token_id": 1,
22
+ "quantization_config": {
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": false,
31
+ "load_in_8bit": true,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "scale_embedding": true,
35
+ "transformers_version": "4.34.0.dev0",
36
+ "use_cache": false,
37
+ "vocab_size": 256008
38
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
3
+ size 4920706
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<madeupword0>",
4
+ "<madeupword1>",
5
+ "<madeupword2>",
6
+ "<madeupword3>",
7
+ "<madeupword4>",
8
+ "<madeupword5>",
9
+ "<madeupword6>"
10
+ ],
11
+ "bos_token": "<s>",
12
+ "cls_token": "<s>",
13
+ "eos_token": "</s>",
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "unk_token": "<unk>"
17
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "256001": {
36
+ "content": "<madeupword0>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "256002": {
44
+ "content": "<madeupword1>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "256003": {
52
+ "content": "<madeupword2>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "256004": {
60
+ "content": "<madeupword3>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "256005": {
68
+ "content": "<madeupword4>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "256006": {
76
+ "content": "<madeupword5>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "256007": {
84
+ "content": "<madeupword6>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ }
91
+ },
92
+ "additional_special_tokens": [
93
+ "<madeupword0>",
94
+ "<madeupword1>",
95
+ "<madeupword2>",
96
+ "<madeupword3>",
97
+ "<madeupword4>",
98
+ "<madeupword5>",
99
+ "<madeupword6>"
100
+ ],
101
+ "bos_token": "<s>",
102
+ "clean_up_tokenization_spaces": true,
103
+ "cls_token": "<s>",
104
+ "eos_token": "</s>",
105
+ "model_max_length": 2048,
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "sp_model_kwargs": {},
109
+ "tokenizer_class": "XGLMTokenizer",
110
+ "tokenizer_file": null,
111
+ "trust_remote_code": false,
112
+ "unk_token": "<unk>",
113
+ "use_fast": true
114
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37cf7b7b4beffb21d83094cff03a1aad5bc580cb2dfe05235777d40470f5242
3
+ size 4475