thxcode/llama3:8b-instruct

Manifest digest

sha256:b56560a93ae89f02c9c8a702fc3dcea0662edd923f5e1218c74dc90f211009c4

OS/ARCH

linux/arm64

Compressed size

2.9 GB

Last pushed

about 2 years by thxcode

Type

Image

Manifest digest

sha256:b56560a93ae89f02c9c8a702fc3dcea0662edd923f5e1218c74dc90f211009c4

Image Layers

1LABEL gguf.model.from=Hugging Face0 B

2LABEL gguf.model.usage=text-to-text0 B

3LABEL gguf.model.vendor=QuantFactory0 B

4

ADD https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.Q2_K.gguf model.gguf # buildkit

2.9 GB

5CMD ["-m" "model.gguf" "-c" "8192"0 B

Command

LABEL gguf.model.from=Hugging Face