Update README.md

README.md

@@ -23,7 +23,7 @@ Trained against LLaMa 30B 4-bit for 3 epochs with cutoff length 1024, using a mi
 - 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)
 
 ### Compatibility
-This LoRA is compatible with any 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
+This LoRA is compatible with any 7B, 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
 
 ### Prompting
 You should prompt the LoRA the same way you would prompt Alpaca or Alpacino:
@@ -51,8 +51,9 @@ Remember that with lower parameter sizes, the structure of the prompt becomes mo
 
 ### Coming Soon
 - 2048 7B version
-- 1024 and 512 variants of 13B and 7B
-- merged ggml models
+- 512 variants of 13B and 7B
+- merged ggml models for 13B and 7B
+- Tweet fix for 13B and 7B
 
 ### Citations
 Alpaca COT datasets