jtatman
/

pythia-125m-gpt4-llm-cleaned

Generated from Trainer

Model card Files Files and versions Community

jtatman commited on Jun 22

Commit

f95286d

•

1 Parent(s): 22c08c9

Upload GPTNeoXForCausalLM

Files changed (1) hide show

config.json +4 -4

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/pythia-125m-deduped",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -22,9 +22,9 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
   "use_parallel_residual": true,
-  "vocab_size": 50304
 }

 {
+  "_name_or_path": "./pythia-125m-gpt4-llm-cleaned",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
   "transformers_version": "4.41.2",
+  "use_cache": true,
   "use_parallel_residual": true,
+  "vocab_size": 50282
 }