sharpenb commited on
Commit
88db0e1
1 Parent(s): b049b0d

Upload folder using huggingface_hub (#2)

Browse files

- 21638378d0fd4f48a9e506cbd6770c28470ab90a88e3a7d82c94d7242252f1e5 (a84e002a5a0c0fd11f1b6b5f4429d9d6bb23dee8)
- 98cea6b74c391fc3e44622bdfb0582928af016c8b9221fabce040178d652a4a5 (4d0a318421e6d51f19a65dbbfc2a88509b7c9e5f)

added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json CHANGED
@@ -16,7 +16,10 @@
16
  "num_hidden_layers": 50,
17
  "num_key_value_heads": 8,
18
  "quantization_config": {
19
- "bnb_4bit_compute_dtype": "float32",
 
 
 
20
  "bnb_4bit_quant_type": "fp4",
21
  "bnb_4bit_use_double_quant": true,
22
  "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,7 +37,7 @@
34
  "sliding_window": 4096,
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "float16",
37
- "transformers_version": "4.37.2",
38
  "use_cache": false,
39
  "vocab_size": 32032
40
  }
 
16
  "num_hidden_layers": 50,
17
  "num_key_value_heads": 8,
18
  "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "float16",
22
+ "bnb_4bit_quant_storage": "uint8",
23
  "bnb_4bit_quant_type": "fp4",
24
  "bnb_4bit_use_double_quant": true,
25
  "llm_int8_enable_fp32_cpu_offload": false,
 
37
  "sliding_window": 4096,
38
  "tie_word_embeddings": false,
39
  "torch_dtype": "float16",
40
+ "transformers_version": "4.39.1",
41
  "use_cache": false,
42
  "vocab_size": 32032
43
  }
generation_config.json CHANGED
@@ -2,6 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 32000,
5
- "transformers_version": "4.37.2",
6
  "use_cache": false
7
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 32000,
5
+ "transformers_version": "4.39.1",
6
  "use_cache": false
7
  }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
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": "</s>",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": false,
60
+ "use_fast": true
61
+ }