Leonard

Results 4 issues of Leonard

Hi, I'm trying to benchmark a new model (Mistral 7B based, extended 120128 char tokenizer and I'm able to run some tasks without errors (hellaswag, truthfulqa, winogrande) but on some...

The docs mention that you used vLLM for inferencing, but it looks like Orion support hasn't been upstreamed yet: https://github.com/vllm-project/vllm/tree/main/vllm/model_executor/models Can you share the model file or do you have...

I just wrote a quick countdown timer app in rumps - awesome work, really was a cinch! The one question I had is how easy/possible it might be to change...

enhancement

### Problem Description I have a 7900XTX (RDNA3, navi3, gfx1100) card that I'm trying to do some useful LLM work and one of the requirements I have is xformers. I...