jinymusim commited on
Commit
f70c703
·
1 Parent(s): 69016e3

Upload 8 files

Browse files

New Model with token limit 1024

Files changed (4) hide show
  1. merges.txt +1 -1
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +7 -1
  4. tokenizer_config.json +1 -1
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ã Ń
3
  Ã ¡
4
  Ġ p
 
1
+ #version: 0.2
2
  Ã Ń
3
  Ã ¡
4
  Ġ p
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae6532129654abe85ad03f722bd48af118bebd5d733e6d8b910d9c6d0086b12f
3
  size 510398013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a567f19d1007dfde526c36eeb570acc2ac2bc49adb8e630d2257dad8c6b2a2
3
  size 510398013
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -39,6 +44,7 @@
39
  "continuing_subword_prefix": "",
40
  "end_of_word_suffix": "",
41
  "fuse_unk": false,
 
42
  "vocab": {
43
  "<|endoftext|>": 0,
44
  "!": 1,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
44
  "continuing_subword_prefix": "",
45
  "end_of_word_suffix": "",
46
  "fuse_unk": false,
47
+ "byte_fallback": false,
48
  "vocab": {
49
  "<|endoftext|>": 0,
50
  "!": 1,
tokenizer_config.json CHANGED
@@ -18,7 +18,7 @@
18
  "single_word": false
19
  },
20
  "errors": "replace",
21
- "model_max_length": 512,
22
  "pad_token": {
23
  "__type": "AddedToken",
24
  "content": "<|endoftext|>",
 
18
  "single_word": false
19
  },
20
  "errors": "replace",
21
+ "model_max_length": 1024,
22
  "pad_token": {
23
  "__type": "AddedToken",
24
  "content": "<|endoftext|>",