CohenQu
/

DeepSeek-R1-Distill-Qwen-7B-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

CohenQu commited on 2 days ago

Commit

e160221

·

verified ·

1 Parent(s): 3a8fff7

End of training

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 base_model: agentica-org/DeepScaleR-1.5B-Preview
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-7B-GRPO
 tags:
@@ -11,7 +12,7 @@ licence: license
 # Model Card for DeepSeek-R1-Distill-Qwen-7B-GRPO
-This model is a fine-tuned version of [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: agentica-org/DeepScaleR-1.5B-Preview
+datasets: hf-cmu-collab/DeepScaleR-1.5B-Preview_on-policy_GRPO
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-7B-GRPO
 tags:
 # Model Card for DeepSeek-R1-Distill-Qwen-7B-GRPO
+This model is a fine-tuned version of [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview) on the [hf-cmu-collab/DeepScaleR-1.5B-Preview_on-policy_GRPO](https://huggingface.co/datasets/hf-cmu-collab/DeepScaleR-1.5B-Preview_on-policy_GRPO) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start