Hugging Face's logo

mradermacher
/
Viking-7B-GGUF

Transformers
GGUF
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
241345f
·
verified ·
1 Parent(s): 7208b15

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -26,7 +26,7 @@ quantized_by: mradermacher
26
  static quants of https://huggingface.co/LumiOpen/Viking-7B
27
 
28
  <!-- provided-files -->
29
- 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.
30
  ## Usage
31
 
32
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -43,10 +43,14 @@ more details, including on how to concatenate multi-part files.
43
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended |
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q6_K.gguf) | Q6_K | 6.3 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality |
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
26
  static quants of https://huggingface.co/LumiOpen/Viking-7B
27
 
28
  <!-- provided-files -->
29
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Viking-7B-i1-GGUF
30
  ## Usage
31
 
32
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
43
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.IQ4_XS.gguf) | IQ4_XS | 4.3 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q6_K.gguf) | Q6_K | 6.3 | very good quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Viking-7B-GGUF/resolve/main/Viking-7B.f16.gguf) | f16 | 15.2 | 16 bpw, overkill |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):