Upload GPTNeoXForCausalLM

config.json

@@ -10,21 +10,21 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 8192,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 57344,
+  "intermediate_size": 7168,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
   "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "num_hidden_layers": 16,
   "pad_token_id": 0,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.5,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50281

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 0,
   "eos_token_id": 0,
   "pad_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383f0994660dcb4c92601cf8ed1def53ae28daeac30456dc7b8496d6c35ddaad
-size 2357751968
+oid sha256:d706f84ddf1399b349d7f6e3be5d4af4a9fcc8254804651d009a641ea87653cd
+size 3891683344