Quick and correct GGUF fashions to your CPU
GGUF is a binary file format designed for environment friendly storage and quick massive language mannequin (LLM) loading with GGML, a C-based tensor library for machine studying.
GGUF encapsulates all needed parts for inference, together with the tokenizer and code, inside a single file. It helps the conversion of assorted language fashions, reminiscent of Llama 3, Phi, and Qwen2. Moreover, it facilitates mannequin quantization to decrease precisions to enhance pace and reminiscence effectivity on CPUs.
We regularly write “GGUF quantization” however GGUF itself is simply a file format, not a quantization methodology. There are a number of quantization algorithms applied in llama.cpp to cut back the mannequin dimension and serialize the ensuing mannequin within the GGUF format.
On this article, we’ll see the way to precisely quantize an LLM and convert it to GGUF, utilizing an significance matrix (imatrix) and the Ok-Quantization methodology. I present the GGUF conversion code for Gemma 2 Instruct, utilizing an imatrix. It really works the identical with different fashions supported by llama.cpp: Qwen2, Llama 3, Phi-3, and so on. We can even see the way to consider the accuracy of the quantization and inference throughput of the ensuing fashions.