Merge branch 'main' of https://huggingface.co/kaiokendev/supercot-lora

README.md

@@ -7,20 +7,19 @@ SuperCOT is a LoRA I trained with the aim of making LLaMa follow prompts for Lan
 Trained against LLaMa 30B 4-bit for 3 epochs with cutoff length 1024, using a mixture of the following datasets:
 
 [https://huggingface.co/datasets/QingyiSi/Alpaca-CoT](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
-
-Chain of thought QED
-
-Chain of thought Aqua
-
-CodeAlpaca
+- Chain of thought QED
+- Chain of thought Aqua
+- CodeAlpaca
 
 [https://huggingface.co/datasets/neulab/conala](https://huggingface.co/datasets/neulab/conala)
-
-Code snippets
+- Code snippets
 
 [https://huggingface.co/datasets/yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned)
+- Alpaca GPT4
 
-Alpaca GPT4
+### Merged Models
+- [https://huggingface.co/gozfarb/llama-30b-supercot-ggml](https://huggingface.co/gozfarb/llama-30b-supercot-ggml)
+- [https://huggingface.co/ausboss/llama-30b-supercot](https://huggingface.co/ausboss/llama-30b-supercot)
 
 ### Compatibility
 This LoRA is compatible with any 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins