Randomly initialized model with my hyperparams

config.json

@@ -1,19 +1,19 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "_name_or_path": "roneneldan/TinyStories-3M",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPTNeoForCausalLM"
+    "GPTNeoModel"
   ],
   "attention_dropout": 0,
   "attention_layers": [
     "global",
-    "local",
     "global",
-    "local",
     "global",
-    "local",
     "global",
-    "local"
+    "global",
+    "global",
+    "global",
+    "global"
   ],
   "attention_types": [
     [
@@ -25,6 +25,7 @@
     ]
   ],
   "bos_token_id": 50256,
+  "classifier_dropout": 0.0,
   "embed_dropout": 0,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
@@ -32,18 +33,18 @@
   "initializer_range": 0.02,
   "intermediate_size": null,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 256,
   "model_type": "gpt_neo",
   "num_heads": 16,
   "num_layers": 8,
   "resid_dropout": 0,
   "summary_activation": null,
-  "summary_first_dropout": 0.1,
+  "summary_first_dropout": 0.0,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.0",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 50257,
   "window_size": 256

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4f93a86407a3f685520e48481a236c7b5e3a4f8e4fc8d1e58f3a748d97a37c
-size 66708541
+oid sha256:b9601b9f78f60eb681e3e3a684b0c9252cb2536c7f7e16c48e39514bd3a3fdf6
+size 32205816