Hugging Face's logo

mradermacher
/
Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
4fab08e
•
1 Parent(s): 0696844

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -33,14 +33,13 @@ more details, including on how to concatenate multi-part files.
33
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
35
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
36
- | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
37
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
42
 
43
-
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
46
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
35
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
36
+ | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
37
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA-GGUF/resolve/main/Yarn-Mistral-7b-128k-SFT-Capybara-QLoRA.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
42
 
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
45