Hugging Face's logo

mradermacher
/
Azathoth-16x7B-bf16-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
8209fd7
·
verified ·
1 Parent(s): da113ae

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -4,7 +4,8 @@ language:
4
  - en
5
  library_name: transformers
6
  license: apache-2.0
7
- no_imatrix: "Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very low-bit quantization"
 
8
  quantized_by: mradermacher
9
  tags:
10
  - moe
@@ -20,7 +21,6 @@ tags:
20
  static quants of https://huggingface.co/Kquant03/Azathoth-16x7B-bf16
21
 
22
  <!-- provided-files -->
23
- 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.
24
  ## Usage
25
 
26
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -37,9 +37,11 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_S.gguf) | Q3_K_S | 39.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_M.gguf) | Q3_K_M | 43.9 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_L.gguf) | Q3_K_L | 47.5 | |
 
40
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_S.gguf.part2of2) | Q4_K_S | 52.3 | fast, recommended |
41
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_M.gguf.part2of2) | Q4_K_M | 55.7 | fast, recommended |
42
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_S.gguf.part2of2) | Q5_K_S | 63.2 | |
 
43
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q6_K.gguf.part2of2) | Q6_K | 75.4 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q8_0.gguf.part2of2) | Q8_0 | 97.6 | fast, best quality |
45
 
 
4
  - en
5
  library_name: transformers
6
  license: apache-2.0
7
+ no_imatrix: Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very
8
+ low-bit quantization
9
  quantized_by: mradermacher
10
  tags:
11
  - moe
 
21
  static quants of https://huggingface.co/Kquant03/Azathoth-16x7B-bf16
22
 
23
  <!-- provided-files -->
 
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/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_S.gguf) | Q3_K_S | 39.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_M.gguf) | Q3_K_M | 43.9 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q3_K_L.gguf) | Q3_K_L | 47.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.IQ4_XS.gguf) | IQ4_XS | 49.5 | |
41
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_S.gguf.part2of2) | Q4_K_S | 52.3 | fast, recommended |
42
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q4_K_M.gguf.part2of2) | Q4_K_M | 55.7 | fast, recommended |
43
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_S.gguf.part2of2) | Q5_K_S | 63.2 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q5_K_M.gguf.part2of2) | Q5_K_M | 65.2 | |
45
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q6_K.gguf.part2of2) | Q6_K | 75.4 | very good quality |
46
  | [PART 1](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Azathoth-16x7B-bf16-GGUF/resolve/main/Azathoth-16x7B-bf16.Q8_0.gguf.part2of2) | Q8_0 | 97.6 | fast, best quality |
47