Michael Feil commited on
Commit
b9e4031
1 Parent(s): d9ea613

initial commit Pythia-Chat-Base-7B to ctranslate2

Browse files
Files changed (5) hide show
  1. config.json +5 -0
  2. model.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +9 -0
  5. vocabulary.txt +0 -0
config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1bd56046d63059409d592568ab9c3603092bd6a28fdd2de77b3874ef8c778b
3
+ size 6863965184
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "name_or_path": "EleutherAI/pythia-6.9b-deduped",
6
+ "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocabulary.txt ADDED
The diff for this file is too large to render. See raw diff