Hugging Face's logo

mradermacher
/
CabraMistral7b-v2-GGUF

Transformers
GGUF
Portuguese
English
text-generation-inference
mistral
brazil
brasil
portuguese
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
65428f0
•
1 Parent(s): e6a3fdd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  base_model: nicolasdec/CabraMistral7b-v2
3
  language:
 
4
  - en
5
  library_name: transformers
6
  license: cc
@@ -42,14 +43,13 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
43
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
45
- | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
46
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
49
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
50
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
51
 
52
-
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55
 
 
1
  ---
2
  base_model: nicolasdec/CabraMistral7b-v2
3
  language:
4
+ - pt
5
  - en
6
  library_name: transformers
7
  license: cc
 
43
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
44
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
45
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
47
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
49
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
50
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/CabraMistral7b-v2-GGUF/resolve/main/CabraMistral7b-v2.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55