Hugging Face's logo

hon9kon9ize
/
yi-1.5-6b-yue-vocab-expanded

Text Generation
Transformers
Safetensors
llama
llama-factory
freeze
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
indiejoseph commited on
Commit
941c288
•
1 Parent(s): c8baa53

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +2 -2
  2. model-00001-of-00005.safetensors +2 -2
  3. model-00005-of-00005.safetensors +2 -2
  4. model.safetensors.index.json +1 -1
  5. special_tokens_map.json +27 -4
  6. tokenizer.model +2 -2
  7. tokenizer_config.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/notebooks/cantonese/llm/models/yi-1.5-6b-yue-expanded",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -25,5 +25,5 @@
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.40.2",
27
  "use_cache": true,
28
- "vocab_size": 67264
29
  }
 
1
  {
2
+ "_name_or_path": "01-ai/Yi-1.5-6B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.40.2",
27
  "use_cache": true,
28
+ "vocab_size": 67456
29
  }
model-00001-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a50f15c06855bf194a583dbd4fcc39935b7e20f5b1936772cb4ebca6e1ab6289
3
- size 4893873904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3265c8962ce1e71b80b0039e780608f8fb8c491f5510b393f8bd083bfcafbf8b
3
+ size 4897019632
model-00005-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cbd7dc23665a2d6864cf4546588c735d35121bb475347b384ee9a5eb1001ca8
3
- size 4923283192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6d129ade15fdab2884e23f1a459a577208df68103c39f3a7fe39b86e052813
3
+ size 4926428920
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 24351096832
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00005-of-00005.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 24357388288
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00005-of-00005.safetensors",
special_tokens_map.json CHANGED
@@ -1,29 +1,52 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<|startoftext|>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
- "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|Human|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|Assistant|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
  "bos_token": {
26
  "content": "<|startoftext|>",
27
  "lstrip": false,
28
+ "normalized": false,
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
  "eos_token": {
33
  "content": "<|endoftext|>",
34
  "lstrip": false,
35
+ "normalized": false,
36
  "rstrip": false,
37
  "single_word": false
38
  },
39
  "pad_token": {
40
  "content": "<unk>",
41
  "lstrip": false,
42
+ "normalized": false,
43
  "rstrip": false,
44
  "single_word": false
45
  },
46
  "unk_token": {
47
  "content": "<unk>",
48
  "lstrip": false,
49
+ "normalized": false,
50
  "rstrip": false,
51
  "single_word": false
52
  }
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
- size 1033105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701049bc2838520e8fb6561477505175af8d06be4952e321e32dbf8e9bb5c01a
3
+ size 1083475
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff