rexwang8 commited on
Commit
f19ad60
1 Parent(s): ff2cb4b

Upload 6 files

Browse files
.ready.txt ADDED
File without changes
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/shakespeare-data/models/rexwang8/py125",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "gradient_checkpointing": true,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "rotary_emb_base": 10000,
19
+ "rotary_pct": 0.25,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.25.1",
23
+ "use_cache": false,
24
+ "use_parallel_residual": true,
25
+ "vocab_size": 50277
26
+ }
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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "/shakespeare-data/models/rexwang8/py125",
7
+ "pad_token": "",
8
+ "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
9
+ "tokenizer_class": "GPTNeoXTokenizer",
10
+ "unk_token": "<|endoftext|>"
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddd4254d3caa3e2f2372b91eb8514f43c3dc9de1e0bacfd9dd0524d80ab46b1
3
+ size 4795