xingyu1996 commited on
Commit
8b2acfa
·
verified ·
1 Parent(s): adcef1f

Upload model weights, config, and tokenizer

Browse files
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50257,
3
+ "n_positions": 512,
4
+ "n_embd": 768,
5
+ "n_layer": 12,
6
+ "n_head": 12,
7
+ "activation_function": "gelu_new",
8
+ "resid_pdrop": 0.1,
9
+ "embd_pdrop": 0.1,
10
+ "attn_pdrop": 0.1,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "initializer_range": 0.02,
13
+ "bos_token_id": 50256,
14
+ "eos_token_id": 50256,
15
+ "model_type": "gpt2"
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f638151f4657d543a5fe1469d387e70500261db2cb33b7fbbcae37cb0cf2509e
3
+ size 650523342
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff