gate369 commited on
Commit
8a1734e
·
verified ·
1 Parent(s): 0e2b5c4

Upload Tiny Epstein 100M model

Browse files
Files changed (4) hide show
  1. config.json +15 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +12 -0
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50257,
3
+ "emb_dim": 1536,
4
+ "hidden_dim": 6144,
5
+ "num_layers": 24,
6
+ "num_heads": 16,
7
+ "num_kv_heads": 8,
8
+ "max_seq_len": 1024,
9
+ "window_size": 1024,
10
+ "sliding_window_ratio": 0.75,
11
+ "rope_theta": 10000.0,
12
+ "dtype": "torch.float16",
13
+ "bias": false,
14
+ "dropout": 0.0
15
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7146a9123f4808d7097476d11d4c4da951cec800a822a82225413a7811a97b
3
+ size 3706392747
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }