HuggingFaceTB
/

SmolVLM-Instruct-DPO

Image-Text-to-Text

Model card Files Files and versions

kashif HF Staff commited on Nov 26, 2024

Commit

478a8e1

·

verified ·

1 Parent(s): a52815c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -94,11 +94,11 @@ print(generated_texts[0])
 ### Training Data
-[ HuggingFaceH4/rlaif-v_formatted](HTTP://huggingface.co/HuggingFaceH4/rlaif-v_formatted)
 ### Training Procedure
-See detailed blog on preference tuning VLLMs [here](https://huggingface.co/blog/dpo_vlm).
 ```bash
 accelerate launch  --config_file examples/accelerate_configs/multi_gpu.yaml \

 ### Training Data
+[HuggingFaceH4/rlaif-v_formatted](https://huggingface.co/datasets/HuggingFaceH4/rlaif-v_formatted)
 ### Training Procedure
+See the detailed blog on preference tuning VLLMs [here](https://huggingface.co/blog/dpo_vlm).
 ```bash
 accelerate launch  --config_file examples/accelerate_configs/multi_gpu.yaml \