copy Ray2333/gpt2-large-harmless-reward_model

config.json

@@ -1,9 +1,8 @@
 {
-  "_name_or_path": "./weak_rm/best_checkpoint",
-  "pipeline_tag": "text-classification",
+  "_name_or_path": "Ray2333/gpt2-large-harmless-reward_model",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2Model"
+    "GPT2ForSequenceClassification"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
@@ -24,7 +23,6 @@
   "n_inner": null,
   "n_layer": 36,
   "n_positions": 1024,
-  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -40,8 +38,8 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
-  "use_cache": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
   "vocab_size": 50257
 }