Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Upload new k-quant GGML quantised models.

Update README.md

Updating model files

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

Delete gpt4-alpaca-lora_mlp-65B.ggml.q5_1.bin

Delete gpt4-alpaca-lora_mlp-65B.ggml.q5_0.bin

Delete gpt4-alpaca-lora_mlp-65B.ggml.q4_0.bin

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

Update README.md

Commit GGML models. These models are only compatible with llama.cpp from May 12th onwards

initial commit