Update README.md

README.md

@@ -27,12 +27,15 @@ It uses a mixture of the following datasets:
 - GGML 30B 4-bit: [https://huggingface.co/gozfarb/llama-30b-supercot-ggml](https://huggingface.co/gozfarb/llama-30b-supercot-ggml)
 - 30B (unquantized): [https://huggingface.co/ausboss/llama-30b-supercot](https://huggingface.co/ausboss/llama-30b-supercot)
 - 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)
+- 30B 4-bit 128g TRITON: N/A
+- 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)
 
 #### 13B
+- GGML 13B 4-bit: [https://huggingface.co/gozfarb/llama-13b-supercot-ggml](https://huggingface.co/gozfarb/llama-13b-supercot-ggml)
 - 13B (unquantized): [https://huggingface.co/ausboss/llama-13b-supercot](https://huggingface.co/ausboss/llama-13b-supercot)
 - 13B 4-bit 128g CUDA: [https://huggingface.co/ausboss/llama-13b-supercot-4bit-128g](https://huggingface.co/ausboss/llama-13b-supercot-4bit-128g)
 - 13B 4-bit 128g TRITON: [https://huggingface.co/TheYuriLover/llama-13b-SuperCOT-4bit-TRITON](https://huggingface.co/TheYuriLover/llama-13b-SuperCOT-4bit-TRITON)
-- GGML 13B 4-bit: [https://huggingface.co/gozfarb/llama-13b-supercot-ggml](https://huggingface.co/gozfarb/llama-13b-supercot-ggml)
+- 13B 4-bit CUDA (no groupsize, better VRAM): N/A
 
 (Thanks to all the awesome anons with supercomputers)