Hugging Face's logo

mradermacher
/
karakuri-lm-70b-v0.1-GGUF

Transformers
GGUF
Japanese
English
llama
llama-2
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
7a21b4e
·
verified ·
1 Parent(s): 2799ee9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -38,7 +38,16 @@ more details, including on how to concatenate multi-part files.
38
 
39
  | Link | Type | Size/GB | Notes |
40
  |:-----|:-----|--------:|:------|
 
 
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q4_K_S.gguf) | Q4_K_S | 39.5 | fast, recommended |
 
 
 
 
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
38
 
39
  | Link | Type | Size/GB | Notes |
40
  |:-----|:-----|--------:|:------|
41
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q2_K.gguf) | Q2_K | 25.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q3_K_S.gguf) | Q3_K_S | 30.2 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q3_K_M.gguf) | Q3_K_M | 33.5 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q3_K_L.gguf) | Q3_K_L | 36.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q4_K_S.gguf) | Q4_K_S | 39.5 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q4_K_M.gguf) | Q4_K_M | 41.7 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q5_K_S.gguf) | Q5_K_S | 47.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q5_K_M.gguf) | Q5_K_M | 49.0 | |
49
+ | [PART 1](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q6_K.gguf.part2of2) | Q6_K | 56.9 | very good quality |
50
+ | [PART 1](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/karakuri-lm-70b-v0.1-GGUF/resolve/main/karakuri-lm-70b-v0.1.Q8_0.gguf.part2of2) | Q8_0 | 73.6 | fast, best quality |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):