mradermacher commited on
Commit
127a96e
·
verified ·
1 Parent(s): 6e20d4a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -45,8 +45,14 @@ more details, including on how to concatenate multi-part files.
45
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_L.gguf) | Q3_K_L | 4.0 | |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
 
 
 
49
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
 
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
45
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q3_K_L.gguf) | Q3_K_L | 4.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.IQ4_XS.gguf) | IQ4_XS | 4.1 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q5_K_S.gguf) | Q5_K_S | 5.2 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q5_K_M.gguf) | Q5_K_M | 5.3 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF/resolve/main/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku.f16.gguf) | f16 | 14.8 | 16 bpw, overkill |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):