Hugging Face's logo

kaiokendev
/
SuperCOT-LoRA

Model card Files Community
2
kaiokendev commited on
Commit
d96160d
•
1 Parent(s): 61e5599

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -31,6 +31,7 @@ It uses a mixture of the following datasets:
31
  - 30B 4-bit 128g CUDA: [https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda)
32
  - 30B 4-bit 128g TRITON: N/A
33
  - 30B 4-bit CUDA (no groupsize, better VRAM): [https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda)
 
34
 
35
  #### 13B
36
  - GGML 13B 4-bit: [https://huggingface.co/gozfarb/llama-13b-supercot-ggml](https://huggingface.co/gozfarb/llama-13b-supercot-ggml)
 
31
  - 30B 4-bit 128g CUDA: [https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda)
32
  - 30B 4-bit 128g TRITON: N/A
33
  - 30B 4-bit CUDA (no groupsize, better VRAM): [https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda)
34
+ - 30B 3-bit 128g CUDA: [https://huggingface.co/tsumeone/llama-30b-supercot-3bit-128g-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-3bit-128g-cuda)
35
 
36
  #### 13B
37
  - GGML 13B 4-bit: [https://huggingface.co/gozfarb/llama-13b-supercot-ggml](https://huggingface.co/gozfarb/llama-13b-supercot-ggml)