Upload GPTNeoXForCausalLM

config.json

@@ -1,47 +1,29 @@
 {
   "_name_or_path": "here_merged",
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPTNeoForCausalLM"
+    "GPTNeoXForCausalLM"
   ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      2
-    ]
-  ],
-  "bos_token_id": 50256,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
   "classifier_dropout": 0.1,
-  "embed_dropout": 0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "hidden_size": 768,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 256,
   "initializer_range": 0.02,
-  "intermediate_size": null,
-  "layer_norm_epsilon": 1e-05,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 16,
-  "num_layers": 4,
-  "resid_dropout": 0,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.33.2",
   "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
+  "use_parallel_residual": true,
+  "vocab_size": 50304
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.33.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d1a7582cd2f7c9e8e69203c56f7b7a40ae0999d4e8677a67f56f4dc74335a
-size 274074521
+oid sha256:fea1f494cfab1c5c10929e1e188288c8d72c525e8a5ba7454815426274379892
+size 122006247