mradermacher commited on
Commit
c7daafc
1 Parent(s): 75386a3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -1
README.md CHANGED
@@ -21,7 +21,7 @@ tags:
21
  static quants of https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0
22
 
23
  <!-- provided-files -->
24
- 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.
25
  ## Usage
26
 
27
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -37,7 +37,16 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q2_K.gguf) | Q2_K | 1.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q3_K_S.gguf) | Q3_K_S | 1.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended |
 
 
 
 
 
 
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):
 
21
  static quants of https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0
22
 
23
  <!-- provided-files -->
24
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-i1-GGUF
25
  ## Usage
26
 
27
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
37
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q2_K.gguf) | Q2_K | 1.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q3_K_S.gguf) | Q3_K_S | 1.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q3_K_L.gguf) | Q3_K_L | 1.6 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.IQ4_XS.gguf) | IQ4_XS | 1.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.8 | fast on arm, low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q5_K_S.gguf) | Q5_K_S | 2.1 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q5_K_M.gguf) | Q5_K_M | 2.2 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q6_K.gguf) | Q6_K | 2.5 | very good quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.Q8_0.gguf) | Q8_0 | 3.2 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Minerva-3B-base-v1.0-GGUF/resolve/main/Minerva-3B-base-v1.0.f16.gguf) | f16 | 5.9 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):