dhuynh95 commited on
Commit
3254f95
β€’
1 Parent(s): 8e00083

Training in progress, epoch 0

Browse files
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "k_proj",
24
+ "up_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5640f420333763f9b915a88dc3bbabcdb27f625ac0e6cfa1f9d7d88a0524fb6
3
+ size 319876032
config.json CHANGED
@@ -17,12 +17,24 @@
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 32,
19
  "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
20
  "rms_norm_eps": 1e-05,
21
  "rope_scaling": null,
22
  "rope_theta": 1000000,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float32",
25
  "transformers_version": "4.37.0.dev0",
26
- "use_cache": true,
27
  "vocab_size": 32016
28
  }
 
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 32,
19
  "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": true,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
  "rms_norm_eps": 1e-05,
33
  "rope_scaling": null,
34
  "rope_theta": 1000000,
35
  "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
  "transformers_version": "4.37.0.dev0",
38
+ "use_cache": false,
39
  "vocab_size": 32016
40
  }
special_tokens_map.json CHANGED
@@ -1,10 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "▁<PRE>",
4
- "▁<MID>",
5
- "▁<SUF>",
6
- "▁<EOT>"
7
- ],
8
  "bos_token": {
9
  "content": "<s>",
10
  "lstrip": false,
@@ -19,6 +13,7 @@
19
  "rstrip": false,
20
  "single_word": false
21
  },
 
22
  "unk_token": {
23
  "content": "<unk>",
24
  "lstrip": false,
 
1
  {
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -25,59 +25,19 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "32007": {
30
- "content": "▁<PRE>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32008": {
38
- "content": "▁<SUF>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32009": {
46
- "content": "▁<MID>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32010": {
54
- "content": "▁<EOT>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
  }
61
  },
62
- "additional_special_tokens": [
63
- "▁<PRE>",
64
- "▁<MID>",
65
- "▁<SUF>",
66
- "▁<EOT>"
67
- ],
68
  "bos_token": "<s>",
69
  "clean_up_tokenization_spaces": false,
70
  "eos_token": "</s>",
71
- "eot_token": "▁<EOT>",
72
- "fill_token": "<FILL_ME>",
73
- "legacy": null,
74
- "middle_token": "▁<MID>",
75
  "model_max_length": 1000000000000000019884624838656,
76
- "pad_token": null,
77
- "prefix_token": "▁<PRE>",
78
  "sp_model_kwargs": {},
79
- "suffix_token": "▁<SUF>",
80
- "tokenizer_class": "CodeLlamaTokenizer",
 
81
  "unk_token": "<unk>",
82
- "use_default_system_prompt": false
 
83
  }
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
 
 
 
 
 
 
30
  "bos_token": "<s>",
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
33
+ "legacy": true,
 
 
 
34
  "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
 
36
  "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
  "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
  }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef7e944707a960f35d3883ae6a57b0933d26a8b89fd1e62dedc69edfc6c87e5
3
+ size 4859