Hugging Face's logo

mradermacher
/
Nous-Puffin-70B-GGUF

Transformers
GGUF
English
llama-2
sft
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
4a7bfe9
•
1 Parent(s): 5d60a7d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -3,7 +3,7 @@ base_model: NousResearch/Nous-Puffin-70B
3
  datasets:
4
  - LDJnr/Puffin
5
  language:
6
- - en
7
  library_name: transformers
8
  license:
9
  - mit
@@ -49,7 +49,6 @@ more details, including on how to concatenate multi-part files.
49
  | [PART 1](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
50
  | [PART 1](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
51
 
52
-
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55
 
 
3
  datasets:
4
  - LDJnr/Puffin
5
  language:
6
+ - eng
7
  library_name: transformers
8
  license:
9
  - mit
 
49
  | [PART 1](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
50
  | [PART 1](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nous-Puffin-70B-GGUF/resolve/main/Nous-Puffin-70B.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
51
 
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
54