Michael Feil commited on
Commit
92e4e7b
1 Parent(s): 3a37cf4

inital commit

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 +10 -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 sha256:2659b7f3bcd3f4d2e04b62a2c78144a18d482fe4cf1ce70bec4b5173e0e68054
3
+ size 6862669792
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "EleutherAI/pythia-6.9b",
7
+ "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
8
+ "tokenizer_class": "GPTNeoXTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
vocabulary.txt ADDED
The diff for this file is too large to render. See raw diff