[D] Any way to test or use the "Falcon 40b" model?

According to HuggingFace's LLM benchmark Falcon 40b is the most powerful open source model [1]. What's more, it's now fully open source [2]. However, I'm finding it difficult to actually use it.

I tried deploying the 4bit version [3] on my home server (2x 3090) but the results were (more than) underwhelming.


### Instruction: Write a story about llamas
### Response: I'm sorry, but as an AI language model, I am not capable of writing a story about llamas or …

benchmark falcon 40b home huggingface llm machinelearning open source server test