Quantized version of https://huggingface.co/Snowflake/snowflake-arctic-instruct
Created from commit be318cae5aba5291208f27d30991a5150500887d. The original model was changed due to fixes for GQA support, so I decided to convert it again.
There is no support for this in mainline llama.cpp yet. You have to use snowflake-arctic branch: https://github.com/fairydreaming/llama.cpp/tree/snowflake-arctic
- Downloads last month
- 99
Model size
479B params
Architecture
arctic
Unable to determine this model's library. Check the
docs
.