Michael Feil commited on
Commit
a8a7103
1 Parent(s): 10424b3

initial commit pythia-12b 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 sha256:82758e96ddd9329922cfc81a8fe473226aabe4983aac3e97a860be5626ebee5a
3
+ size 11855209712
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/gpt-neox-20b",
6
+ "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/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