Locutusque
commited on
Commit
•
976904c
1
Parent(s):
b723019
Upload tokenizer
Browse files- README.md +3 -3
- tokenizer_config.json +7 -0
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
library_name: transformers
|
3 |
tags:
|
4 |
- code
|
5 |
- chemistry
|
6 |
- medical
|
7 |
-
license: other
|
8 |
datasets:
|
9 |
- Locutusque/hyperion-v3.0
|
10 |
-
language:
|
11 |
-
- en
|
12 |
---
|
13 |
# Locutusque/Hyperion-3.0-Yi-34B
|
14 |
## Model Details
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: other
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- code
|
8 |
- chemistry
|
9 |
- medical
|
|
|
10 |
datasets:
|
11 |
- Locutusque/hyperion-v3.0
|
|
|
|
|
12 |
---
|
13 |
# Locutusque/Hyperion-3.0-Yi-34B
|
14 |
## Model Details
|
tokenizer_config.json
CHANGED
@@ -31,10 +31,17 @@
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "<|endoftext|>",
|
33 |
"legacy": true,
|
|
|
34 |
"model_max_length": 4096,
|
|
|
35 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
36 |
"sp_model_kwargs": {},
|
|
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
38 |
"unk_token": "<unk>",
|
39 |
"use_default_system_prompt": false
|
40 |
}
|
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "<|endoftext|>",
|
33 |
"legacy": true,
|
34 |
+
"max_length": 512,
|
35 |
"model_max_length": 4096,
|
36 |
+
"pad_to_multiple_of": null,
|
37 |
"pad_token": "<|endoftext|>",
|
38 |
+
"pad_token_type_id": 0,
|
39 |
+
"padding_side": "left",
|
40 |
"sp_model_kwargs": {},
|
41 |
+
"stride": 0,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"truncation_side": "right",
|
44 |
+
"truncation_strategy": "longest_first",
|
45 |
"unk_token": "<unk>",
|
46 |
"use_default_system_prompt": false
|
47 |
}
|