mradermacher commited on
Commit
40424ea
·
verified ·
1 Parent(s): 6afa327

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -5,6 +5,10 @@ language:
5
  library_name: transformers
6
  license: gemma
7
  quantized_by: mradermacher
 
 
 
 
8
  ---
9
  ## About
10
 
@@ -16,7 +20,7 @@ quantized_by: mradermacher
16
  static quants of https://huggingface.co/Tesslate/Synthia-S1-27b
17
 
18
  <!-- provided-files -->
19
- 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.
20
  ## Usage
21
 
22
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -33,8 +37,12 @@ more details, including on how to concatenate multi-part files.
33
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_S.gguf) | Q3_K_S | 12.3 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_M.gguf) | Q3_K_M | 13.5 | lower quality |
35
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_L.gguf) | Q3_K_L | 14.6 | |
 
36
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
37
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q4_K_M.gguf) | Q4_K_M | 16.6 | fast, recommended |
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q8_0.gguf) | Q8_0 | 28.8 | fast, best quality |
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
5
  library_name: transformers
6
  license: gemma
7
  quantized_by: mradermacher
8
+ tags:
9
+ - generated_from_trainer
10
+ - trl
11
+ - sft
12
  ---
13
  ## About
14
 
 
20
  static quants of https://huggingface.co/Tesslate/Synthia-S1-27b
21
 
22
  <!-- provided-files -->
23
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Synthia-S1-27b-i1-GGUF
24
  ## Usage
25
 
26
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
37
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_S.gguf) | Q3_K_S | 12.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_M.gguf) | Q3_K_M | 13.5 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q3_K_L.gguf) | Q3_K_L | 14.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.IQ4_XS.gguf) | IQ4_XS | 15.0 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q4_K_M.gguf) | Q4_K_M | 16.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q5_K_S.gguf) | Q5_K_S | 18.9 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q5_K_M.gguf) | Q5_K_M | 19.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q6_K.gguf) | Q6_K | 22.3 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Synthia-S1-27b-GGUF/resolve/main/Synthia-S1-27b.Q8_0.gguf) | Q8_0 | 28.8 | fast, best quality |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant