XueyingJia
/

Qwen2-1.5B-Instruct-ours-4-epoch

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

XueyingJia commited on Dec 12, 2024

Commit

fac7105

·

verified ·

1 Parent(s): 6472600

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-Instruct-ours-2-epoch-merge
 library_name: transformers
 model_name: Qwen2-1.5B-Instruct-ours-4-epoch
 tags:
@@ -11,7 +12,7 @@ licence: license
 # Model Card for Qwen2-1.5B-Instruct-ours-4-epoch
-This model is a fine-tuned version of [XueyingJia/Qwen2-1.5B-Instruct-ours-2-epoch-merge](https://huggingface.co/XueyingJia/Qwen2-1.5B-Instruct-ours-2-epoch-merge).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: XueyingJia/Qwen2-1.5B-Instruct-ours-2-epoch-merge
+datasets: XueyingJia/hh-rlhf-train-filtered
 library_name: transformers
 model_name: Qwen2-1.5B-Instruct-ours-4-epoch
 tags:
 # Model Card for Qwen2-1.5B-Instruct-ours-4-epoch
+This model is a fine-tuned version of [XueyingJia/Qwen2-1.5B-Instruct-ours-2-epoch-merge](https://huggingface.co/XueyingJia/Qwen2-1.5B-Instruct-ours-2-epoch-merge) on the [XueyingJia/hh-rlhf-train-filtered](https://huggingface.co/datasets/XueyingJia/hh-rlhf-train-filtered) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start