JayHyeon
/

Qwen_0.5-VDPO_5e-7-3ep_10vpo_const

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

JayHyeon commited on Feb 8

Commit

0b7749a

·

verified ·

1 Parent(s): fd0b8d3

End of training

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 base_model: JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep
 library_name: transformers
 model_name: Qwen_0.5-VDPO_5e-7-3ep_10vpo_const
 tags:
@@ -11,7 +12,7 @@ licence: license
 # Model Card for Qwen_0.5-VDPO_5e-7-3ep_10vpo_const
-This model is a fine-tuned version of [JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep](https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep
+datasets: trl-lib/ultrafeedback_binarized
 library_name: transformers
 model_name: Qwen_0.5-VDPO_5e-7-3ep_10vpo_const
 tags:
 # Model Card for Qwen_0.5-VDPO_5e-7-3ep_10vpo_const
+This model is a fine-tuned version of [JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep](https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep) on the [trl-lib/ultrafeedback_binarized](https://huggingface.co/datasets/trl-lib/ultrafeedback_binarized) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start