match new script name (#34)

Update Windows executable naming as per llama.cpp changes

Update Windows executable naming as per llama.cpp changes

Update README.md

Upload requirements.txt

Update README.md

Update README.md

Rename gguf-imat-llama-3.py to gguf-imat-for-FP16.py

Rename gguf-imat-llama-3-lossless-for-BF16.py to gguf-imat-lossless-for-BF16.py

Rename gguf-imat-llama-3-lossless.py to gguf-imat-llama-3-lossless-for-BF16.py

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Add back llama-3 script in previous state.

Rename script.

Upload gguf-imat-llama-3.py (#30)

Update README.md

Update README.md

Update README.md

Update README.md (#28)

llama.cpp/#6920 warning

https://github.com/ggerganov/llama.cpp/pull/6920 (#26)

Forgot to double check. (#24)

Update README.md

Script parity. Handle error. (#20)

Update README.md

Delete extra-files

Update README.md

More fixes. (#17)

More fixes. (#16)

Update README.md

Temp WIP. (#15)

Adjust config folder link.

Add Llama-3 (#14)

Upload 3 files (#13)

Update README.md

Update README.md

Update README.md

Fix things. (#12)

Fix lines.

Fix lines.

Fix lines.

Atribute credits directly.

Atribute credits directly.

Add checks for F16.gguf and imatrix.dat, as well make HF model removal optional by default. (#11)