Hugging Face's logo

mradermacher
/
jais-family-30b-16k-chat-GGUF

Transformers
GGUF
Arabic
English
Arabic
English
LLM
Decoder
causal-lm
jais-family
conversational
Model card Files Community
mradermacher commited on
Commit
0a2d842
·
verified ·
1 Parent(s): 6ce7354

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -24,7 +24,7 @@ tags:
24
  static quants of https://huggingface.co/inceptionai/jais-family-30b-16k-chat
25
 
26
  <!-- provided-files -->
27
- 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.
28
  ## Usage
29
 
30
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -41,7 +41,11 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_S.gguf) | Q3_K_S | 23.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_M.gguf) | Q3_K_M | 25.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_L.gguf) | Q3_K_L | 25.5 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q4_K_S.gguf) | Q4_K_S | 27.1 | fast, recommended |
 
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q6_K.gguf) | Q6_K | 33.2 | very good quality |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
24
  static quants of https://huggingface.co/inceptionai/jais-family-30b-16k-chat
25
 
26
  <!-- provided-files -->
27
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/jais-family-30b-16k-chat-i1-GGUF
28
  ## Usage
29
 
30
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
41
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_S.gguf) | Q3_K_S | 23.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_M.gguf) | Q3_K_M | 25.2 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q3_K_L.gguf) | Q3_K_L | 25.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.IQ4_XS.gguf) | IQ4_XS | 26.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q4_K_S.gguf) | Q4_K_S | 27.1 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q4_K_M.gguf) | Q4_K_M | 28.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q5_K_S.gguf) | Q5_K_S | 30.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q5_K_M.gguf) | Q5_K_M | 31.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/jais-family-30b-16k-chat-GGUF/resolve/main/jais-family-30b-16k-chat.Q6_K.gguf) | Q6_K | 33.2 | very good quality |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant