SuratanBoonpong commited on
Commit
b632a7f
·
verified ·
1 Parent(s): 99ac4bc

Training in progress, epoch 0

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "openthaigpt/openthai-llama-pretrained-7B",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,13 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_proj",
23
- "gate_proj",
24
  "up_proj",
25
- "o_proj",
26
  "down_proj",
27
- "k_proj",
28
- "q_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "aisingapore/sea-lion-7b",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "up_proj",
23
+ "Wqkv",
24
  "down_proj",
25
+ "out_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:367be43ab244f105ece84561f042736ba3dbdeba0ec3b2562090d749a7135aaf
3
- size 2205725864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9a3a4d9b5a9408898bf12ec7351e3a568f5bc66ba8dfb8b8675af0755378e4
3
+ size 5268115352
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "<|im_end|>": 56541,
3
- "<|im_start|>": 56542
4
  }
 
1
  {
2
+ "<|im_end|>": 256000,
3
+ "<|im_start|>": 256001
4
  }
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77901fd826845fd170d28f7c5eb4edf599ee7baa58e9e1c5bd4f527ca26f4893
3
- size 1167962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05234874580b169d3ba5a59b004b655ddba73fc9ea5493451053374629d9295d
3
+ size 4569957
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "add_bos_token": true,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
@@ -11,22 +11,14 @@
11
  "special": true
12
  },
13
  "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "56541": {
30
  "content": "<|im_end|>",
31
  "lstrip": false,
32
  "normalized": false,
@@ -34,7 +26,7 @@
34
  "single_word": false,
35
  "special": true
36
  },
37
- "56542": {
38
  "content": "<|im_start|>",
39
  "lstrip": false,
40
  "normalized": false,
@@ -47,18 +39,20 @@
47
  "<|im_end|>",
48
  "<|im_start|>"
49
  ],
 
 
 
 
 
 
50
  "bos_token": "<|im_start|>",
51
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
52
  "clean_up_tokenization_spaces": false,
53
  "eos_token": "<|im_end|>",
54
  "legacy": true,
55
- "model_max_length": 2048,
56
  "pad_token": "<|im_end|>",
57
- "padding_side": "right",
58
  "sp_model_kwargs": {},
59
- "spaces_between_special_tokens": false,
60
- "tokenizer_class": "LlamaTokenizer",
61
- "unk_token": "<unk>",
62
- "use_default_system_prompt": true,
63
- "use_fast": false
64
  }
 
1
  {
2
+ "add_bos_token": false,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
 
11
  "special": true
12
  },
13
  "1": {
14
+ "content": "<|endoftext|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "256000": {
 
 
 
 
 
 
 
 
22
  "content": "<|im_end|>",
23
  "lstrip": false,
24
  "normalized": false,
 
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "256001": {
30
  "content": "<|im_start|>",
31
  "lstrip": false,
32
  "normalized": false,
 
39
  "<|im_end|>",
40
  "<|im_start|>"
41
  ],
42
+ "auto_map": {
43
+ "AutoTokenizer": [
44
+ "aisingapore/sea-lion-7b--tokenization_SEA_BPE.SEABPETokenizer",
45
+ null
46
+ ]
47
+ },
48
  "bos_token": "<|im_start|>",
49
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
  "clean_up_tokenization_spaces": false,
51
  "eos_token": "<|im_end|>",
52
  "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
  "pad_token": "<|im_end|>",
 
55
  "sp_model_kwargs": {},
56
+ "tokenizer_class": "SEABPETokenizer",
57
+ "unk_token": "<unk>"
 
 
 
58
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4004d7da3d39076aa7611d1e7a258a89be164ebf6b8626f5fa1f2ca3f6de5c
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419b3860314b7dd22027263011a6fc33d709dad949e5f6c86f81266b11502fe7
3
  size 4728