mradermacher commited on
Commit
80720ce
·
verified ·
1 Parent(s): 226d796

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -46,7 +46,7 @@ quantized_by: mradermacher
46
  static quants of https://huggingface.co/jondurbin/bagel-dpo-8x7b-v0.2
47
 
48
  <!-- provided-files -->
49
- 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.
50
  ## Usage
51
 
52
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -63,9 +63,11 @@ more details, including on how to concatenate multi-part files.
63
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
64
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
65
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_L.gguf) | Q3_K_L | 24.3 | |
 
66
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
67
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
68
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q5_K_S.gguf) | Q5_K_S | 32.3 | |
 
69
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
70
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
71
 
 
46
  static quants of https://huggingface.co/jondurbin/bagel-dpo-8x7b-v0.2
47
 
48
  <!-- provided-files -->
49
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-i1-GGUF
50
  ## Usage
51
 
52
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
63
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_S.gguf) | Q3_K_S | 20.5 | |
64
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_M.gguf) | Q3_K_M | 22.6 | lower quality |
65
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q3_K_L.gguf) | Q3_K_L | 24.3 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.IQ4_XS.gguf) | IQ4_XS | 25.5 | |
67
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q4_K_S.gguf) | Q4_K_S | 26.8 | fast, recommended |
68
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q4_K_M.gguf) | Q4_K_M | 28.5 | fast, recommended |
69
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q5_K_S.gguf) | Q5_K_S | 32.3 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q5_K_M.gguf) | Q5_K_M | 33.3 | |
71
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q6_K.gguf) | Q6_K | 38.5 | very good quality |
72
  | [GGUF](https://huggingface.co/mradermacher/bagel-dpo-8x7b-v0.2-GGUF/resolve/main/bagel-dpo-8x7b-v0.2.Q8_0.gguf) | Q8_0 | 49.7 | fast, best quality |
73