Nathan Brown

Noticing that non-quantized versions of Llama-3-70B don't seem to be available on Unsloth? For example, here is non-quantized vs 4bit quantized Llama-3-8B: - https://huggingface.co/unsloth/llama-3-8b - https://huggingface.co/unsloth/llama-3-8b-bnb-4bit On the other hand,...

@dumitrac I'm interested in this as well. I'd like to utilize the Dolma toolkit to perform some filtering on CC data (which is what I assume @codefly13 was attempting to...

Got a 404 trying to open that paste? Assuming this is what I believe it to be, it's a known bug with Quizlet-dl not being able to locate the "See...

I haven't tested this on a Jupyter notebook, so I'm unsure what the proper way to run this program would be - all testing I've done has been on my...

Would love to see this feature added. Not having access to the loss inside of compute_metrics() makes it rather difficult to calculate metrics like perplexity.