Hugging Face's logo

mradermacher
/
RewardMistral-7b-v3-GGUF

Transformers
GGUF
English
Generated from Trainer
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
01c48ea
·
verified ·
1 Parent(s): 01c2603

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -33,7 +33,7 @@ more details, including on how to concatenate multi-part files.
33
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
35
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
36
- | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
37
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
@@ -41,7 +41,6 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
42
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.SOURCE.gguf) | SOURCE | 14.6 | source gguf, only provided when it was hard to come by |
43
 
44
-
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):
47
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
35
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
36
+ | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
37
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
38
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
42
  | [GGUF](https://huggingface.co/mradermacher/RewardMistral-7b-v3-GGUF/resolve/main/RewardMistral-7b-v3.SOURCE.gguf) | SOURCE | 14.6 | source gguf, only provided when it was hard to come by |
43
 
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
46