add readme and fix docker.sh

README.md

@@ -0,0 +1,28 @@
+Convert-to-Quant (`ctq`) is installed for normal quantizations.
+`hf`, the Hugging Face CLI command, and llama.cpp's compiled binaries are also available.
+
+For GGUF quantizations, try:
+- `hf_to_nvfp4_quant` (huggingface structure to GGUF)
+- `gguf_to_nvfp4_quant` (GGUF to GGUF)
+- `safetensors_to_nvfp4_quant` (ComfyUI style safetensors to GGUF (untested))
+- `hf_to_nvfp4_safetensors` (huggingface structure to ComfyUI style safetensors)
+
+For model info, try:
+- `hf_info` (huggingface structure)
+- `gguf_info` (GGUF structure)
+---
+
+Example:
+
+```bash
+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
+```
+
+This would create a NVFP4 GGUF for Ollama/llama.cpp from `https://huggingface.co/coder3101/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`
+
+Conversions between formats without quantization is available in the custom commands with `--no-quant`.

docker.sh

@@ -8,6 +8,7 @@ get_latest() {
 	latest_image=$(docker images --format '{{.CreatedAt}}\t{{.Repository}}:{{.Tag}}' zefie/nvfp4_quant \
 	  | sort -r \
 	  | cut -f2- \
+	  | grep -v latest \
 	  | head -n 1)
 
 	if [[ -z "$latest_image" ]]; then
@@ -44,7 +45,9 @@ elif [ "${1}" == "push" ]; then
 	# push dated one first, then latest
 	"${0}" mklatest
 	IMAGE=$(get_latest)
+	echo "Pushing ${IMAGE}"
 	docker push "${IMAGE}"
+	echo "Pushing zefie/nvfp4_quant:latest"
 	docker push "zefie/nvfp4_quant:latest"
 else
 	echo "Usage: ${0} [build|run|mklatest]"