Update README.md

README.md

@@ -19,14 +19,14 @@ license: other
 
 # Allen AI's Tulu 30B merged with Kaio Ken's SuperHOT 8K fp16
 
-These files are pytorch format fp16 model files for [Allen AI's Tulu 30B merged with Kaio Ken's SuperHOT 8K](https://huggingface.co/allenai/tulu-65b).
+These files are fp16 model files for [Allen AI's Tulu 30B](https://huggingface.co/allenai/tulu-30b) merged with [Kaio Ken's SuperHOT 30B 8K LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test) to produce a model capable of 8K context.
+
+[Kaio Ken's SuperHOT 30B LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test) is merged on to the base model to produce a model capable of 8K context, via a modified version of the Llama modelling code.
 
-It is the result of merging and/or converting the source repository to float16.
 
 ## Repositories available
 
-* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Tulu-30B-SuperHOT-8K-fp16)
-* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/none)
+* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Tulu-30B-SuperHOT-8K-GPTQ)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Tulu-30B-SuperHOT-8K-fp16)
 
 <!-- footer start -->