jingyaogong commited on
Commit
8c0c0de
·
verified ·
1 Parent(s): e9c2b1b

Upload 7 files

Browse files
config.json CHANGED
@@ -20,12 +20,10 @@
20
  "num_key_value_heads": 2,
21
  "pretraining_tp": 1,
22
  "rms_norm_eps": 1e-05,
23
- "rope_parameters": {
24
- "rope_theta": 1000000.0,
25
- "rope_type": "default"
26
- },
27
  "tie_word_embeddings": true,
28
- "transformers_version": "5.0.0rc0",
29
  "use_cache": true,
30
  "vocab_size": 6400
31
  }
 
20
  "num_key_value_heads": 2,
21
  "pretraining_tp": 1,
22
  "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000.0,
 
 
25
  "tie_word_embeddings": true,
26
+ "transformers_version": "4.57.1",
27
  "use_cache": true,
28
  "vocab_size": 6400
29
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "5.0.0rc0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.57.1"
6
  }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|im_start|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json CHANGED
@@ -2,18 +2,42 @@
2
  "add_bos_token": false,
3
  "add_eos_token": false,
4
  "add_prefix_space": false,
5
- "additional_special_tokens": null,
6
- "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "bos_token": "<|im_start|>",
8
  "clean_up_tokenization_spaces": false,
9
  "eos_token": "<|im_end|>",
10
- "extra_special_tokens": [],
11
- "is_local": true,
12
  "legacy": true,
13
  "model_max_length": 32768,
14
  "pad_token": "<|endoftext|>",
15
  "sp_model_kwargs": {},
16
  "spaces_between_special_tokens": false,
17
- "tokenizer_class": "TokenizersBackend",
18
  "unk_token": "<|endoftext|>"
19
  }
 
2
  "add_bos_token": false,
3
  "add_eos_token": false,
4
  "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
  "bos_token": "<|im_start|>",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "<|im_end|>",
35
+ "extra_special_tokens": {},
 
36
  "legacy": true,
37
  "model_max_length": 32768,
38
  "pad_token": "<|endoftext|>",
39
  "sp_model_kwargs": {},
40
  "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "PreTrainedTokenizerFast",
42
  "unk_token": "<|endoftext|>"
43
  }