Hugging Face's logo

mradermacher
/
bloomz-mt-GGUF

Transformers
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
a547c8d
•
1 Parent(s): 4a1e085

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -63,7 +63,7 @@ quantized_by: mradermacher
63
  static quants of https://huggingface.co/bigscience/bloomz-mt
64
 
65
  <!-- provided-files -->
66
- 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.
67
  ## Usage
68
 
69
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -79,7 +79,12 @@ more details, including on how to concatenate multi-part files.
79
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q2_K.gguf.part2of2) | Q2_K | 68.2 | |
80
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_S.gguf.part2of2) | Q3_K_S | 78.8 | |
81
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_M.gguf.part2of2) | Q3_K_M | 94.5 | lower quality |
 
82
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part3of3) | Q4_K_S | 103.1 | fast, recommended |
 
 
 
 
83
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part3of3) | Q6_K | 147.7 | very good quality |
84
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part4of4) | Q8_0 | 191.2 | fast, best quality |
85
 
 
63
  static quants of https://huggingface.co/bigscience/bloomz-mt
64
 
65
  <!-- provided-files -->
66
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/bloomz-mt-i1-GGUF
67
  ## Usage
68
 
69
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
79
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q2_K.gguf.part2of2) | Q2_K | 68.2 | |
80
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_S.gguf.part2of2) | Q3_K_S | 78.8 | |
81
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_M.gguf.part2of2) | Q3_K_M | 94.5 | lower quality |
82
+ | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.IQ4_XS.gguf.part2of2) | IQ4_XS | 97.8 | |
83
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_S.gguf.part3of3) | Q4_K_S | 103.1 | fast, recommended |
84
+ | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q3_K_L.gguf.part3of3) | Q3_K_L | 103.1 | |
85
+ | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q4_K_M.gguf.part3of3) | Q4_K_M | 114.8 | fast, recommended |
86
+ | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_S.gguf.part3of3) | Q5_K_S | 124.3 | |
87
+ | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q5_K_M.gguf.part3of3) | Q5_K_M | 133.7 | |
88
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q6_K.gguf.part3of3) | Q6_K | 147.7 | very good quality |
89
  | [PART 1](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/bloomz-mt-GGUF/resolve/main/bloomz-mt.Q8_0.gguf.part4of4) | Q8_0 | 191.2 | fast, best quality |
90