JayHyeon
/

pythia-2.8b-VDPO_5e-7_10.0vpo_constant-1ep

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

JayHyeon commited on Jun 24

Commit

60c9705

·

verified ·

1 Parent(s): 2a90786

End of training

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 base_model: EleutherAI/pythia-2.8b
 library_name: transformers
 model_name: pythia-2.8b-VDPO_5e-7_10.0vpo_constant-1ep
 tags:
@@ -11,7 +12,7 @@ licence: license
 # Model Card for pythia-2.8b-VDPO_5e-7_10.0vpo_constant-1ep
-This model is a fine-tuned version of [EleutherAI/pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: EleutherAI/pythia-2.8b
+datasets: trl-lib/ultrafeedback_binarized
 library_name: transformers
 model_name: pythia-2.8b-VDPO_5e-7_10.0vpo_constant-1ep
 tags:
 # Model Card for pythia-2.8b-VDPO_5e-7_10.0vpo_constant-1ep
+This model is a fine-tuned version of [EleutherAI/pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) 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