Métriques du dépôt
- Stars
- (16 227 stars)
- Métriques de merge PR
- (Merge moyen 4j) (2 PRs mergées en 30 j)
Description
⚙️ Request New Models
- Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf
- Is this model architecture supported by MLC-LLM? Yes
Additional context
I know others have made this request already (https://github.com/mlc-ai/mlc-llm/issues/2246, https://github.com/mlc-ai/mlc-llm/pull/2222, https://github.com/mlc-ai/mlc-llm/issues/2238, https://github.com/mlc-ai/mlc-llm/issues/2205).
But I am requesting something different: I am suggesting that you do not quantize or modify the weights of the model but that you instead use Microsoft's already 4-bit quantized weights.
The reason is that I suspect (although it is not explicit in their repo) they used quantization-aware training to build these GGUF files. I have tested the regular 32-bit model vs the GGUF 4-bit one and the performance is almost equivalent which is not what I've seen so far with MLC's quantized models (they tend to be more inaccurate compared to their 32-bit counterparts).
Is there a way to use Microsoft's own quantized weights?
Thank you! Federico