mikeogezi
/

Qwen2-VL-2B-GRPO-MMR-NoRationale

Image-Text-to-Text

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mikeogezi commited on 8 days ago

Commit

8161e7b

·

verified ·

1 Parent(s): bd440c8

End of training

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,5 +1,6 @@
 ---
 base_model: Qwen/Qwen2-VL-2B-Instruct
 library_name: transformers
 model_name: Qwen2-VL-2B-GRPO-MMR-NoRationale
 tags:
@@ -9,7 +10,7 @@ licence: license
 # Model Card for Qwen2-VL-2B-GRPO-MMR-NoRationale
-This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: Qwen/Qwen2-VL-2B-Instruct
+datasets: mikeogezi/res_1k
 library_name: transformers
 model_name: Qwen2-VL-2B-GRPO-MMR-NoRationale
 tags:
 # Model Card for Qwen2-VL-2B-GRPO-MMR-NoRationale
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the [mikeogezi/res_1k](https://huggingface.co/datasets/mikeogezi/res_1k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start