Upload model

README.md

@@ -5,6 +5,7 @@ license: apache-2.0
 tags:
 - gpt2
 - dpo
+- trl
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - Intel/orca_dpo_pairs

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Sharathhebbar24/chat_gpt2",
+  "_name_or_path": "openai-community/gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,11 +12,13 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 24,
   "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -33,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9518982e1e24453360266d7b9c1ab25b8895bff8e166ad1b1b716a284f85d70
-size 497774208
+oid sha256:45668770622f973a85d1263a4a59659158c7915c22f6266b2ad34ce8cb63c21a
+size 1419322880