Edit model card

Please check merge.yml for more information about the contents of this model.

This model is the result of a dare ties merge of two of the most performant 7B models (Go-Bruins and Bagel-DPO) alongside the best RP merge, Toppy M. The purpose of this merge was to create an intelligent assistant model that could engage in RP as easily as it answered questions.

I have briefly tested this model and have been very happy with its performance.

FP16 model available here: https://huggingface.co/jeiku/Rosa_v1_7B

Downloads last month
23
GGUF
Model size
7.24B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

16-bit

Unable to determine this model's library. Check the docs .