Hugging Face's logo

mradermacher
/
CantoneseLLM-6B-preview202402-GGUF

Transformers
GGUF
Yue Chinese
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
abc5a70
·
verified ·
1 Parent(s): f827ce2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -35,10 +35,14 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_S.gguf) | Q3_K_S | 2.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_L.gguf) | Q3_K_L | 3.3 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended |
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q6_K.gguf) | Q6_K | 5.1 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality |
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
35
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_S.gguf) | Q3_K_S | 2.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q3_K_L.gguf) | Q3_K_L | 3.3 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.IQ4_XS.gguf) | IQ4_XS | 3.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q4_K_M.gguf) | Q4_K_M | 3.8 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q5_K_S.gguf) | Q5_K_S | 4.3 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q5_K_M.gguf) | Q5_K_M | 4.4 | |
43
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q6_K.gguf) | Q6_K | 5.1 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/CantoneseLLM-6B-preview202402-GGUF/resolve/main/CantoneseLLM-6B-preview202402.f16.gguf) | f16 | 12.2 | 16 bpw, overkill |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):