Initial GGML model commit

README.md

@@ -56,6 +56,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Kimiko-v2-13B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Kimiko-v2-13B-GGUF)
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Kimiko-v2-13B-GGML)
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Kimiko-v2-13B-fp16)
 * [nRuaif's original LoRA adapter, which can be merged on to the base model.](https://huggingface.co/nRuaif/Kimiko-v2-13B)
 
 ## Prompt template: Vicuna