kyujinpy commited on
Commit
58b36c8
1 Parent(s): 4fcc3f7

Upload 8 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
config.json CHANGED
@@ -1,25 +1,29 @@
1
  {
2
- "_name_or_path": "meta-llama/Llama-2-13b-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
6
  "bos_token_id": 1,
 
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
9
  "hidden_size": 5120,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 13824,
12
- "max_position_embeddings": 4096,
13
  "model_type": "llama",
14
  "num_attention_heads": 40,
15
  "num_hidden_layers": 40,
16
  "num_key_value_heads": 40,
 
17
  "pretraining_tp": 1,
18
  "rms_norm_eps": 1e-05,
19
  "rope_scaling": null,
 
20
  "tie_word_embeddings": false,
21
  "torch_dtype": "float16",
22
- "transformers_version": "4.32.1",
23
  "use_cache": true,
24
  "vocab_size": 32000
25
  }
 
1
  {
2
+ "_name_or_path": "hyunseoki/ko-en-llama2-13b",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "bos_token_id": 1,
8
+ "drop_path_rate": 0.0,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
  "hidden_size": 5120,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 13824,
14
+ "max_position_embeddings": 2048,
15
  "model_type": "llama",
16
  "num_attention_heads": 40,
17
  "num_hidden_layers": 40,
18
  "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float16",
26
+ "transformers_version": "4.34.0",
27
  "use_cache": true,
28
  "vocab_size": 32000
29
  }
generation_config.json CHANGED
@@ -1,10 +1,7 @@
1
  {
 
2
  "bos_token_id": 1,
3
- "do_sample": true,
4
  "eos_token_id": 2,
5
- "max_length": 4096,
6
  "pad_token_id": 0,
7
- "temperature": 0.6,
8
- "top_p": 0.9,
9
- "transformers_version": "4.32.1"
10
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 1,
 
4
  "eos_token_id": 2,
 
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.34.0"
 
 
7
  }
special_tokens_map.json CHANGED
@@ -1,23 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": false,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": false,
31
  "special": true
32
  }
33
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": true,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": true,
31
  "special": true
32
  }
33
  ],
tokenizer_config.json CHANGED
@@ -1,34 +1,39 @@
1
  {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
10
  "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
- "padding_side": "right",
23
  "sp_model_kwargs": {},
24
  "tokenizer_class": "LlamaTokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- },
33
  "use_default_system_prompt": true
34
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
  "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
 
 
 
 
 
 
 
33
  "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
 
35
  "sp_model_kwargs": {},
36
  "tokenizer_class": "LlamaTokenizer",
37
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
38
  "use_default_system_prompt": true
39
  }