trasposed

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "FinancialSupport/NanoGPT",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -13,9 +14,13 @@
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
+  "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -27,5 +32,8 @@
       "max_length": 50
     }
   },
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
   "vocab_size": 50257
-}
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb107f46ecb49dbe5228fe911762c7d6e906863c18a20a3c3e3df5f6b8c1b93
-size 497802202
+oid sha256:1e2b46dce21fa5f3a92525ef6fec0a61166665f54ff753b80d36f68c512cf79e
+size 497805594