Update README.md

README.md

@@ -40,7 +40,7 @@ widget:
 - drag vae decoder(s), i.e., vae, to illustrious_vae folder (./ComfyUI/models/vae)
 
 ### **run it straight (no installation needed way)**
-- get the comfy pack with the new gguf-node ([beta](https://github.com/calcuis/gguf/releases))
+- get the comfy pack with the new gguf-node ([pack](https://github.com/calcuis/gguf/releases))
 - run the .bat file in the main directory
 
 ### **workflow**
@@ -50,7 +50,7 @@ widget:
 ### **review**
 - use tag/word(s) as input for more accurate results for those legacy models; not very convenient (compare to the recent models) at the very beginning
 - credits should be given to those contributors from civitai platform
-- **fast-illustrious gguf** was quantized from **fp8** scaled safetensors while **illustrious gguf** was quantized from the original **bf16** (this is just an attempt to test: is it true? the trimmed model with 50% tensors less really faster? test it yourself)
+- **fast-illustrious gguf** was quantized from **fp8** scaled safetensors while **illustrious gguf** was quantized from the original **bf16** (this is just an attempt to test: is it true? the trimmed model with 50% tensors less really load faster? please test it yourself; some models might have their unique structure/feature, not applicable for all)
 - fp8 scaled file works fine in this model; including vae and clips
 - good to run on old machines, i.e., 9xx series or before (legacy mode [--disable-cuda-malloc --lowvram] supported); compatible with the new gguf-node