dmayhem93 commited on
Commit
645258b
1 Parent(s): f0758b4

Upload GPTNeoXForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +25 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/nvme/home/dakota/ckpts/pythia/125m-sft-self-critiquing-refine/checkpoint-4713",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "gpt_neox",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "rotary_emb_base": 10000,
18
+ "rotary_pct": 0.25,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.26.0.dev0",
22
+ "use_cache": true,
23
+ "use_parallel_residual": true,
24
+ "vocab_size": 50304
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699602bd0686dbcbb592b659c3de69ab94e86cdea6e547e01e996c6afe52f2eb
3
+ size 699682733