mradermacher commited on
Commit
2f6a343
·
verified ·
1 Parent(s): 0630862

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -33,7 +33,7 @@ tags:
33
  static quants of https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-64k
34
 
35
  <!-- provided-files -->
36
- 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.
37
  ## Usage
38
 
39
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -50,8 +50,11 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
 
 
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
 
33
  static quants of https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-64k
34
 
35
  <!-- provided-files -->
36
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-i1-GGUF
37
  ## Usage
38
 
39
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
50
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
59
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
60
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-64k-GGUF/resolve/main/Llama-3-8B-Instruct-64k.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |