Hugging Face's logo

mradermacher
/
quill-72b-instruct-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
0f15857
•
1 Parent(s): 594dfd8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -45,6 +45,7 @@ more details, including on how to concatenate multi-part files.
45
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
46
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
47
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
 
45
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
46
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
47
  | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
48
+ | [PART 1](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.SOURCE.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.SOURCE.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/quill-72b-instruct-GGUF/resolve/main/quill-72b-instruct.SOURCE.gguf.part3of3) | SOURCE | 145.5 | source gguf, only provided when it was hard to come by |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):