Import legacy Q4_1 quantization (created w/ imatrix)

Import IQ4_NL (4.5 bpw) quantization

Import Q4_0 (legacy) quantization

Swap Q3_K_L for new IQ4_XS quantization

Import updated Q5_K_M quantization

Import updated Q3_K_L quantization

Update Q6_K quantization to imatrix version (take 2)

Import updated Q5_K_S quantization

Update Q6_K quantization to imatrix version

Update Q4_K_S quantization to imatrix version

Update Q4_K_M quantization to imatrix version

Import importance matrix and source data

Remove Q5_K_M quantization; it is unable to download (hash mismatch)

Update Q4_K_M quantization to GGUFv2

Update Q4_K_S quantization to GGUFv2

Remove legacy quantizations (Q4_0, Q5_0)

Update Q5_K_M quantization to GGUFv2

Update Q6_K quantization to GGUFv2

Import Q6_K quantization

Import Q4_K_S quantization

Import Q5_0 (legacy) quantization

Import Q4_K_M quantization

Import Q5_K_M quantization

Initial GGUF conversion of gpt4-x-vicuna-13B (Q4_0)

initial commit