mradermacher commited on
Commit
ca176b4
·
verified ·
1 Parent(s): 627b662

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -33,7 +33,19 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
 
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
 
 
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q2_K.gguf) | Q2_K | 0.8 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q3_K_S.gguf) | Q3_K_S | 0.9 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q3_K_L.gguf) | Q3_K_L | 1.0 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.IQ4_XS.gguf) | IQ4_XS | 1.0 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q5_K_S.gguf) | Q5_K_S | 1.2 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q5_K_M.gguf) | Q5_K_M | 1.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q6_K.gguf) | Q6_K | 1.4 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
47
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Caption-Pro-GGUF/resolve/main/Caption-Pro.f16.gguf) | f16 | 3.2 | 16 bpw, overkill |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):