Hugging Face's logo

mradermacher
/
ORCA_LLaMA_70B_QLoRA-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
a9e0a62
•
1 Parent(s): dde4bd9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -15,7 +15,7 @@ quantized_by: mradermacher
15
  static quants of https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA
16
 
17
  <!-- provided-files -->
18
- 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.
19
  ## Usage
20
 
21
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -35,6 +35,9 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
 
 
 
38
  | [PART 1](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
39
  | [PART 1](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
40
 
 
15
  static quants of https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA
16
 
17
  <!-- provided-files -->
18
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-i1-GGUF
19
  ## Usage
20
 
21
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
35
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
36
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
41
  | [PART 1](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
42
  | [PART 1](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ORCA_LLaMA_70B_QLoRA-GGUF/resolve/main/ORCA_LLaMA_70B_QLoRA.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
43