lym00 commited on
Commit
5d78bc6
·
verified ·
1 Parent(s): 7d5896c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -12,8 +12,16 @@ language:
12
  license: apache-2.0
13
  ---
14
 
 
 
15
  This is a GGUF conversion of [vrgamedevgirl84/Wan14BT2VFusionX](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX) with additional VACE functionality.
16
 
 
 
 
 
 
 
17
  The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:
18
 
19
  | Type | Name | Location | Download |
@@ -26,4 +34,8 @@ The model files can be used in [ComfyUI](https://github.com/comfyanonymous/Comfy
26
 
27
  ### Notes
28
 
29
- *As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*
 
 
 
 
 
12
  license: apache-2.0
13
  ---
14
 
15
+ # vrgamedevgirl84/Wan14BT2VFusionX GGUF Conversion
16
+
17
  This is a GGUF conversion of [vrgamedevgirl84/Wan14BT2VFusionX](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX) with additional VACE functionality.
18
 
19
+ All quantized versions were created from the base FP16 model [Wan14BT2VFusioniX_fp16_.safetensors](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/blob/main/Wan14BT2VFusioniX_fp16_.safetensors) using the conversion scripts provided by city96, available at the [ComfyUI-GGUF GitHub repository](https://github.com/city96/ComfyUI-GGUF/tree/main/tools).
20
+
21
+ The process involved first patching and converting the safetensors model to a FP16 GGUF, then quantizing it, and finally applying the 5D fixes.
22
+
23
+ ## Usage
24
+
25
  The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:
26
 
27
  | Type | Name | Location | Download |
 
34
 
35
  ### Notes
36
 
37
+ *As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*
38
+
39
+ ## Reference
40
+
41
+ - For an overview of quantization types, please see the [LLaMA 3 8B Scoreboard quantization chart](https://github.com/ggml-org/llama.cpp/blob/b3962/examples/perplexity/README.md#llama-3-8b-scoreboard).