initial commit

docker/README.txt

@@ -0,0 +1,22 @@
+Convert-to-Quant (ctq) is installed for normal quantizations.
+
+For GGUF quantizations, try:
+
+hf_to_nvfp4_quant
+gguf_to_nvfp4_quant
+safetensors_to_nvfp4_quant
+hf_to_nvfp4_safetensors
+
+Depending on the source material.
+
+hf cli command is also installed, eg you can:
+
+
+hf download coder3101/gemma-4-12B-it-heretic --local-dir gemma-4-12B-it-heretic
+hf_to_nvfp4_gguf -o gemma-4-12B-it-heretic_nvfp4 gemma-4-12B-it-heretic
+
+The same directory can be quantized to one ComfyUI NVFP4 safetensors file:
+
+hf_to_nvfp4_safetensors -o gemma-4-12B-it-heretic-NVFP4.safetensors gemma-4-12B-it-heretic
+
+This would create a NVFP4 GGUF for Ollama/llama.cpp from https://huggingface.co/coder3101/gemma-4-12B-it-heretic

docker/gguf_to_nvfp4_gguf

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /root/nvfp4_gguf_quant/gguf_to_nvfp4_gguf.py --llama-cpp /root/llama.cpp "${@}"

docker/hf_to_nvfp4_gguf

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /root/nvfp4_gguf_quant/hf_to_nvfp4_gguf.py --llama-cpp /root/llama.cpp "${@}"

docker/hf_to_nvfp4_safetensors

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /root/nvfp4_gguf_quant/hf_to_nvfp4_safetensors.py --convert-to-quant /root/convert_to_quant "${@}"

docker/safetensors_to_nvfp4_gguf

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /root/nvfp4_gguf_quant/safetensors_to_nvfp4_gguf.py --llama-cpp /root/llama.cpp "${@}"