Hugging Face's logo

mradermacher
/
lzlv-longLORA-70b-rope8-32k-fp16-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
c07492b
•
1 Parent(s): 98e384e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -28,7 +28,10 @@ more details, including on how to concatenate multi-part files.
28
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q3_K_L.gguf) | Q3_K_L | 36.6 | |
29
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q4_K_S.gguf) | Q4_K_S | 39.7 | fast, medium quality |
30
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q4_K_M.gguf) | Q4_K_M | 41.8 | fast, medium quality |
 
 
31
  | [PART 1](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q6_K.gguf.part2of2) | Q6_K | 57.0 | very good quality |
 
32
 
33
 
34
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
28
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q3_K_L.gguf) | Q3_K_L | 36.6 | |
29
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q4_K_S.gguf) | Q4_K_S | 39.7 | fast, medium quality |
30
  | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q4_K_M.gguf) | Q4_K_M | 41.8 | fast, medium quality |
31
+ | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q5_K_S.gguf) | Q5_K_S | 47.9 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q5_K_M.gguf) | Q5_K_M | 49.2 | |
33
  | [PART 1](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q6_K.gguf.part2of2) | Q6_K | 57.0 | very good quality |
34
+ | [PART 1](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lzlv-longLORA-70b-rope8-32k-fp16-GGUF/resolve/main/lzlv-longLORA-70b-rope8-32k-fp16.Q8_0.gguf.part2of2) | Q8_0 | 73.6 | fast, best quality |
35
 
36
 
37
  Here is a handy graph by ikawrakow comparing some lower-quality quant