llama.cpp
f57fadc0 - Slight quantization improvement for Q4_K and Q5_K (#5361)

Commit

1 year ago

Slight quantization improvement for Q4_K and Q5_K (#5361) * Q4_K: slightly better quantization * Q5_K: slightly better quantization --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

References

#5361 - Slight quantization improvement for Q4_K and Q5_K

Author

ikawrakow

Parents

2e9c0bd6

Files1

ggml-quants.c

llama.cpp f57fadc0 - Slight quantization improvement for Q4_K and Q5_K (#5361)

llama.cpp
f57fadc0 - Slight quantization improvement for Q4_K and Q5_K (#5361)