Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jise/huggingface/runs/45vcoo2g)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jise/huggingface/runs/vzkfljfz)
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 

config.json

@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 32128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c546e89e814f67fee3b9d93f14971ba86981b27414c5a0a00ceba217e1e8c52
+oid sha256:d2f94fb0204d917b9cf6cd06c81e81b0d27d0d245ad36d4bca9f4f5316567a2d
 size 990409330

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec272fcea354bd7efa5035aecb36d92b1027e0713a3ca966357ae7c3fd40be8
+oid sha256:e54fb2b3205e0db9ed0b34d45e7e7004a6cff9512e90a4589c62802fcd2c4866
 size 6072