Hugging Face's logo

mradermacher
/
Babel-9B-Chat-GGUF

Transformers
GGUF
multilingual
babel
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
e94b37a
·
verified ·
1 Parent(s): ee1a062

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -45,7 +45,7 @@ tags:
45
  static quants of https://huggingface.co/Tower-Babel/Babel-9B-Chat
46
 
47
  <!-- provided-files -->
48
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
49
  ## Usage
50
 
51
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -62,11 +62,14 @@ more details, including on how to concatenate multi-part files.
62
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_S.gguf) | Q3_K_S | 4.2 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.6 | lower quality |
64
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.9 | |
 
65
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q4_K_S.gguf) | Q4_K_S | 5.4 | fast, recommended |
66
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.6 | fast, recommended |
67
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q5_K_S.gguf) | Q5_K_S | 6.4 | |
 
68
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q6_K.gguf) | Q6_K | 7.5 | very good quality |
69
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality |
 
70
 
71
  Here is a handy graph by ikawrakow comparing some lower-quality quant
72
  types (lower is better):
 
45
  static quants of https://huggingface.co/Tower-Babel/Babel-9B-Chat
46
 
47
  <!-- provided-files -->
48
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Babel-9B-Chat-i1-GGUF
49
  ## Usage
50
 
51
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
62
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_S.gguf) | Q3_K_S | 4.2 | |
63
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.6 | lower quality |
64
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.9 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.IQ4_XS.gguf) | IQ4_XS | 5.1 | |
66
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q4_K_S.gguf) | Q4_K_S | 5.4 | fast, recommended |
67
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.6 | fast, recommended |
68
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q5_K_S.gguf) | Q5_K_S | 6.4 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q5_K_M.gguf) | Q5_K_M | 6.5 | |
70
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q6_K.gguf) | Q6_K | 7.5 | very good quality |
71
  | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/Babel-9B-Chat-GGUF/resolve/main/Babel-9B-Chat.f16.gguf) | f16 | 18.1 | 16 bpw, overkill |
73
 
74
  Here is a handy graph by ikawrakow comparing some lower-quality quant
75
  types (lower is better):