dranger003's picture
Update README.md
9c3a8a1 verified
|
raw
history blame
874 Bytes
metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: gguf

GGUF importance matrix (imatrix) quants for https://huggingface.co/abacusai/Smaug-Mixtral-v0.1
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.

NOTE: The new IQ3_M/IQ3_S/Q3_K_XS quants are currently causing a segfault during quantization, so I'll upload them once llama.cpp gets fixed. The imatrix is being used on the K-quants as well.

Layers Context Template
32
32768
<s>[INST] {prompt} [/INST]
{response}