kerzgrr commited on
Commit
01c2e6c
·
verified ·
1 Parent(s): 68374f9

Upload 7 files

Browse files
config.json CHANGED
@@ -1,5 +1,7 @@
1
  {
2
- "architectures": ["LlamaForCausalLM"],
 
 
3
  "model_type": "llama",
4
  "vocab_size": 32000,
5
  "hidden_size": 768,
@@ -8,7 +10,7 @@
8
  "num_attention_heads": 12,
9
  "num_key_value_heads": 4,
10
  "hidden_act": "silu",
11
- "rms_norm_eps": 1e-5,
12
  "max_position_embeddings": 1024,
13
  "rope_theta": 10000.0,
14
  "rope_scaling": null,
@@ -20,5 +22,4 @@
20
  "bos_token_id": 2,
21
  "eos_token_id": 6,
22
  "torch_dtype": "bfloat16"
23
- }
24
-
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
  "model_type": "llama",
6
  "vocab_size": 32000,
7
  "hidden_size": 768,
 
10
  "num_attention_heads": 12,
11
  "num_key_value_heads": 4,
12
  "hidden_act": "silu",
13
+ "rms_norm_eps": 1e-05,
14
  "max_position_embeddings": 1024,
15
  "rope_theta": 10000.0,
16
  "rope_scaling": null,
 
22
  "bos_token_id": 2,
23
  "eos_token_id": 6,
24
  "torch_dtype": "bfloat16"
25
+ }
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e16886488717524cd139348a9160e6d1f457fc8cb078751366934a022cbf9a
3
+ size 249349736
special_token_ids.json CHANGED
@@ -6,4 +6,4 @@
6
  "<|start_header_id|>": 4,
7
  "<|end_header_id|>": 5,
8
  "<|eot_id|>": 6
9
- }
 
6
  "<|start_header_id|>": 4,
7
  "<|end_header_id|>": 5,
8
  "<|eot_id|>": 6
9
+ }
special_tokens_map.json CHANGED
@@ -8,4 +8,4 @@
8
  "<|end_header_id|>",
9
  "<|eot_id|>"
10
  ]
11
- }
 
8
  "<|end_header_id|>",
9
  "<|eot_id|>"
10
  ]
11
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,75 +1,13 @@
1
  {
2
- "tokenizer_class": "GPT2TokenizerFast",
3
  "tokenizer_file": "tokenizer.json",
4
- "model_max_length": 1024,
5
- "add_prefix_space": true,
6
- "clean_up_tokenization_spaces": false,
7
- "bos_token": "<|begin_of_text|>",
8
- "eos_token": "<|eot_id|>",
9
  "pad_token": "<|pad|>",
 
 
10
  "unk_token": "<|unk|>",
11
  "additional_special_tokens": [
12
  "<|start_header_id|>",
13
  "<|end_header_id|>",
14
  "<|eot_id|>"
15
  ],
16
- "added_tokens_decoder": {
17
- "0": {
18
- "content": "<|pad|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false,
23
- "special": true
24
- },
25
- "1": {
26
- "content": "<|unk|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false,
31
- "special": true
32
- },
33
- "2": {
34
- "content": "<|begin_of_text|>",
35
- "lstrip": false,
36
- "normalized": false,
37
- "rstrip": false,
38
- "single_word": false,
39
- "special": true
40
- },
41
- "3": {
42
- "content": "<|end_of_text|>",
43
- "lstrip": false,
44
- "normalized": false,
45
- "rstrip": false,
46
- "single_word": false,
47
- "special": true
48
- },
49
- "4": {
50
- "content": "<|start_header_id|>",
51
- "lstrip": false,
52
- "normalized": false,
53
- "rstrip": false,
54
- "single_word": false,
55
- "special": true
56
- },
57
- "5": {
58
- "content": "<|end_header_id|>",
59
- "lstrip": false,
60
- "normalized": false,
61
- "rstrip": false,
62
- "single_word": false,
63
- "special": true
64
- },
65
- "6": {
66
- "content": "<|eot_id|>",
67
- "lstrip": false,
68
- "normalized": false,
69
- "rstrip": false,
70
- "single_word": false,
71
- "special": true
72
- }
73
- },
74
- "chat_template": "{% for message in messages %}{% if loop.first %}<|begin_of_text|>{% endif %}<|start_header_id|>{{ message['role'] }}<|end_header_id|>\n\n{{ message['content'] }}<|eot_id|>{% endfor %}{% if add_generation_prompt %}<|start_header_id|>assistant<|end_header_id|>\n\n{% endif %}"
75
- }
 
1
  {
 
2
  "tokenizer_file": "tokenizer.json",
 
 
 
 
 
3
  "pad_token": "<|pad|>",
4
+ "eos_token": "<|eot_id|>",
5
+ "bos_token": "<|begin_of_text|>",
6
  "unk_token": "<|unk|>",
7
  "additional_special_tokens": [
8
  "<|start_header_id|>",
9
  "<|end_header_id|>",
10
  "<|eot_id|>"
11
  ],
12
+ "add_prefix_space": true
13
+ }