Spaces:

---

MaziyarPanahi

/

FACTS-Leaderboard

like 10

Running

I nominate the new tiny (DeepSeek-R1-0528-Qwen3-8B) and big (DeepSeek-R1-0528) R1 models 👀

I can do the 8B for sure! Stay tuned! 🔥

if possible can you add any model out of this collection (fine tuned models in medical field base on LLaMA-3.1 and Qwen2.5) if you can add 7b and 8b would be intersting to see results
https://huggingface.co/collections/FreedomIntelligence/huatuogpt-o1-677261a3711767cce7c64e13

if possible can you add any model out of this collection (fine tuned models in medical field base on LLaMA-3.1 and Qwen2.5) if you can add 7b and 8b would be intersting to see results
https://huggingface.co/collections/FreedomIntelligence/huatuogpt-o1-677261a3711767cce7c64e13

also someone fine-tuned Qwen3-4b with same dataset:
https://huggingface.co/XformAI-india/Qwen3-4B-medicaldataset

https://huggingface.co/posts/seawolf2357/221417890817416

Hello!

If you know of any open(source) models with a permissive license (MIT, Apache 2.0, or any license that allows commercial use), especially those unique to RAG and medicine, please share a link here. I’ll do my best to include them in the FACTS Grounding leaderboard. 🤗

base: Mistral-Small-3.1-24B-Instruct-2503
LISTING: https://huggingface.co/ginigen/Private-BitSix-Mistral-Small-3.1-24B-Instruct-2503

Hello!

If you know of any open(source) models with a permissive license (MIT, Apache 2.0, or any license that allows commercial use), especially those unique to RAG and medicine, please share a link here. I’ll do my best to include them in the FACTS Grounding leaderboard. 🤗

Thank you for your kind words! I appreciate your interest in having these models evaluated.
QwQ-R1984-32B: https://huggingface.co/VIDraft/QwQ-R1984-32B
Gemma-3-R1984-4B: https://huggingface.co/VIDraft/Gemma-3-R1984-4B
Gemma-3-R1984-12B: https://huggingface.co/VIDraft/Gemma-3-R1984-12B