21 lines
4.3 KiB
Batchfile
21 lines
4.3 KiB
Batchfile
REM python C:\Quanter\llama.cpp\convert_hf_to_gguf.py B:\12B\KrakenSakura-Maelstrom-12B-v1 --outfile B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf --outtype bf16
|
|
C:\Quanter\llama.cpp\llama-quantize B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q2_K.gguf Q2_K
|
|
C:\Quanter\llama.cpp\llama-quantize B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q3_K_M.gguf Q3_K_M
|
|
C:\Quanter\llama.cpp\llama-quantize B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q4_K_M.gguf Q4_K_M
|
|
C:\Quanter\llama.cpp\llama-quantize B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q5_K_M.gguf Q5_K_M
|
|
C:\Quanter\llama.cpp\llama-quantize B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q6_K_M.gguf Q6_K
|
|
python C:\Quanter\llama.cpp\convert_hf_to_gguf.py B:\12B\KrakenSakura-Maelstrom-12B-v1 --outfile B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-Q8_0.gguf --outtype q8_0
|
|
timeout /t 3 /nobreak && cls
|
|
C:\Quanter\llama.cpp\llama-imatrix -m B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf -f C:\Quanter\llama.cpp\illuminati_imatrix_v1.txt -o krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ4_NL.gguf IQ4_NL
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ4_XS.gguf IQ4_XS
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ3_M.gguf IQ3_M
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ3_S.gguf IQ3_S
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ3_XS.gguf IQ3_XS
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ3_XXS.gguf IQ3_XXS
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ2_M.gguf IQ2_M
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ2_S.gguf IQ2_S
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ2_XS.gguf IQ2_XS
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ2_XXS.gguf IQ2_XXS
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ1_M.gguf IQ1_M
|
|
C:\Quanter\llama.cpp\llama-quantize --imatrix krakensakura-maelstrom-12b-v1_illuminati_imatrix_v1.dat input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\input.gguf B:\12B\KrakenSakura-Maelstrom-12B-v1\KrakenSakura-Maelstrom-12B-v1-IQ1_S.gguf IQ1_S |