mradermacher

/

model_requests

like 82

Wow what an awesome model! I for sure will try it out. So cool to see a 72B model beating GPT-4o in medical exams.

@mradermacher I had to force add it because the model author put config.json into LFS for no reason and somehow your metdata check hates it beeing in LFS:

pfnet/Preferred-MedLLM-Qwen-72B: no architectures entry (malformed JSON string, neither tag, array, object, number, string or atom, at character offset 0 (before "version https://git-...") at /llmjob/share/bin/llmjob line 1562.

It's queued! :D

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Preferred-MedLLM-Qwen-72B-GGUF for quants to appear.

somehow your metdata check hates it beeing in LFS

I suspect it downloads the pointer file. Let me try to fix that.

yeah, it was using raw/main. I hope that the huggingface api library resolves it as well (I fall back on the read_text method).