"Update README.md"

README.md

@@ -12,6 +12,16 @@ I'm constantly enhancing these model descriptions to provide you with the most r
 Persimmon is a Large language Model from Adept AI. It is trained from Scratch with a context legth of 16k, which is 4 times the context size of LLaMA2 or ChatGPT and 8 times that of GPT-3
 
 
+---
+# Brief
+This is a preview of adepts persimmon base model.
+It i snot based on the model published at https://huggingface.co/adept/persimmon-8b-base but on the ones released on the tar files in https://github.com/persimmon-ai-labs/adept-inference.
+As these seems to be slightly different, models based on the huggingface release will follow as soon as possible.
+## Note: These models do not seem to work with cuda acceleration at the moment. If you are using the Cublas version of Llama.cpp, you need to set `--n-gpu-layers 0` for it to work. (At a later date this may work again with Cuda, so feel free to play with this setting)
+
+---
+
+
 
 # About GGUF format