zefie 83566ee414 compile llama for the docker

2026-11-01 18:58:34 -05:00

docker

initial commit

2026-11-01 16:31:33 -05:00

llama.cpp

include llama.cpp since there were some edits

2026-11-01 16:32:35 -05:00

nvfp4gguf

improve quantization

2026-11-01 18:30:02 -05:00

.gitignore

some edits

2026-11-01 18:06:11 -05:00

Dockerfile

compile llama for the docker

2026-11-01 18:58:34 -05:00

gguf_info.py

initial commit

2026-11-01 16:31:33 -05:00

gguf_to_nvfp4_gguf.py

improve quantization

2026-11-01 18:30:02 -05:00

hf_info.py

initial commit

2026-11-01 16:31:33 -05:00

hf_to_nvfp4_gguf.py

improve quantization

2026-11-01 18:30:02 -05:00

hf_to_nvfp4_safetensors.py

improve quantization

2026-11-01 18:30:02 -05:00

ollama_nvfp4.py

initial commit

2026-11-01 16:31:33 -05:00

requirements.txt

initial commit

2026-11-01 16:31:33 -05:00

safetensors_to_nvfp4_gguf.py

initial commit

2026-11-01 16:31:33 -05:00

S

Description

Tools to quantize HuggingFace or GGUF models to NVFP4 as GGUF or safetensors.

https://hub.docker.com/repository/docker/zefie/nvfp4_quant

36 MiB

0 Stars 1 Watchers 0 Forks

Languages

Python 98%

Dockerfile 1.3%

Shell 0.7%