mradermacher commited on
Commit
007b41f
·
verified ·
1 Parent(s): f662352

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -19,7 +19,7 @@ tags:
19
  static quants of https://huggingface.co/Nohobby/MS-Schisandra-22B-v0.3
20
 
21
  <!-- provided-files -->
22
- 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.
23
  ## Usage
24
 
25
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -33,8 +33,16 @@ more details, including on how to concatenate multi-part files.
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q2_K.gguf) | Q2_K | 8.4 | |
 
36
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q3_K_M.gguf) | Q3_K_M | 10.9 | lower quality |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q4_K_S.gguf) | Q4_K_S | 12.8 | fast, recommended |
 
 
 
 
 
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
40
  types (lower is better):
 
19
  static quants of https://huggingface.co/Nohobby/MS-Schisandra-22B-v0.3
20
 
21
  <!-- provided-files -->
22
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-i1-GGUF
23
  ## Usage
24
 
25
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q2_K.gguf) | Q2_K | 8.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q3_K_S.gguf) | Q3_K_S | 9.7 | |
37
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q3_K_M.gguf) | Q3_K_M | 10.9 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q3_K_L.gguf) | Q3_K_L | 11.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.IQ4_XS.gguf) | IQ4_XS | 12.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q4_K_S.gguf) | Q4_K_S | 12.8 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q4_K_M.gguf) | Q4_K_M | 13.4 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q5_K_S.gguf) | Q5_K_S | 15.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q5_K_M.gguf) | Q5_K_M | 15.8 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q6_K.gguf) | Q6_K | 18.4 | very good quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.3-GGUF/resolve/main/MS-Schisandra-22B-v0.3.Q8_0.gguf) | Q8_0 | 23.7 | fast, best quality |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):