Audreygyj
/

qwen-1.5b-sft-HH-offline-dpo

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

Audreygyj commited on 16 days ago

Commit

1037d6e

•

1 Parent(s): 0eb96f7

End of training

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 base_model: XueyingJia/Qwen2-1.5B-SFT-merge
 library_name: transformers
 model_name: qwen-1.5b-sft-HH-offline-dpo
 tags:
@@ -11,7 +12,7 @@ licence: license
 # Model Card for qwen-1.5b-sft-HH-offline-dpo
-This model is a fine-tuned version of [XueyingJia/Qwen2-1.5B-SFT-merge](https://huggingface.co/XueyingJia/Qwen2-1.5B-SFT-merge).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: XueyingJia/Qwen2-1.5B-SFT-merge
+datasets: Anthropic/hh-rlhf
 library_name: transformers
 model_name: qwen-1.5b-sft-HH-offline-dpo
 tags:
 # Model Card for qwen-1.5b-sft-HH-offline-dpo
+This model is a fine-tuned version of [XueyingJia/Qwen2-1.5B-SFT-merge](https://huggingface.co/XueyingJia/Qwen2-1.5B-SFT-merge) on the [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start