mradermacher commited on
Commit
b9bcf92
·
verified ·
1 Parent(s): 9d2b7a7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -31,7 +31,7 @@ tags:
31
  static quants of https://huggingface.co/prithivMLmods/Triangulum-5B
32
 
33
  <!-- provided-files -->
34
- 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.
35
  ## Usage
36
 
37
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -48,10 +48,14 @@ more details, including on how to concatenate multi-part files.
48
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_S.gguf) | Q3_K_S | 2.6 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_L.gguf) | Q3_K_L | 3.1 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q4_K_S.gguf) | Q4_K_S | 3.3 | fast, recommended |
52
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended |
 
 
53
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q6_K.gguf) | Q6_K | 4.5 | very good quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q8_0.gguf) | Q8_0 | 5.9 | fast, best quality |
 
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):
 
31
  static quants of https://huggingface.co/prithivMLmods/Triangulum-5B
32
 
33
  <!-- provided-files -->
34
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Triangulum-5B-i1-GGUF
35
  ## Usage
36
 
37
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
48
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_S.gguf) | Q3_K_S | 2.6 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q3_K_L.gguf) | Q3_K_L | 3.1 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.IQ4_XS.gguf) | IQ4_XS | 3.2 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q4_K_S.gguf) | Q4_K_S | 3.3 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q5_K_S.gguf) | Q5_K_S | 3.9 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q5_K_M.gguf) | Q5_K_M | 4.0 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q6_K.gguf) | Q6_K | 4.5 | very good quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.Q8_0.gguf) | Q8_0 | 5.9 | fast, best quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-5B-GGUF/resolve/main/Triangulum-5B.f16.gguf) | f16 | 10.9 | 16 bpw, overkill |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
61
  types (lower is better):