Leo Grinsztajn commited on
Commit
3952a37
1 Parent(s): 63bd2c7

First model version

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "eos_token_id": 0,
7
+ "hidden_act": "gelu",
8
+ "hidden_size": 2048,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 8192,
11
+ "layer_norm_eps": 1e-05,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "gpt_neox",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "rotary_emb_base": 10000,
17
+ "rotary_pct": 0.25,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.24.0",
21
+ "use_cache": true,
22
+ "use_parallel_residual": true,
23
+ "vocab_size": 50304
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bdf84b616b57b909d0569c9b00852a40e47507a8b58cfe9995ffabcf3938f8
3
+ size 5759384017
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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
+ }