Hugging Face's logo

mradermacher
/
llama-3-70B-instruct-uncensored-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
llama
trl
sft
Inference Endpoints
conversational
Model card Files Community
2
mradermacher commited on
Commit
5605775
•
1 Parent(s): 01338fc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -50,7 +50,6 @@ more details, including on how to concatenate multi-part files.
50
  | [PART 1](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
51
  | [PART 1](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
50
  | [PART 1](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
51
  | [PART 1](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-GGUF/resolve/main/llama-3-70B-instruct-uncensored.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55