xx

src/about.py

@@ -87,13 +87,6 @@ An example of llava with vllm as backend:
         --backend vllm \
         --extra-args "--limit-mm-per-prompt image=10 --max-model-len 32768"`
 
-## Icons
-- 🟢 : pretrained model: new, base models, trained on a given corpora
-- 🔶 : fine-tuned on domain-specific datasets model: pretrained models finetuned on more data
-- 💬 : chat models (RLHF, DPO, IFT, ...) model: chat like fine-tunes, either using IFT (datasets of task instruction), RLHF or DPO (changing the model loss a bit with an added policy), etc
-- 🤝 : base merges and moerges model: merges or MoErges, models which have been merged or fused without additional fine-tuning. If there is no icon, we have not uploaded the information on the model yet, feel free to open an issue with the model information!
-"Flagged" indicates that this model has been flagged by the community, and should probably be ignored! Clicking the link will redirect you to the discussion about the model.
-
 ## Useful links
 - [Community resources](https://huggingface.co/spaces/BAAI/open_flageval_vlm_leaderboard/discussions)
 - [FlagEvalMM](https://github.com/flageval-baai/FlagEvalMM)