This is my daily driver, made by finetuning my v1 model with several custom datasets and then merging them together. It's smart enough, it can do prose, it can do roleplaying.

Overall, it's worth a try if you're a 7B enthusiast. Just don't expect it to be better than the sum of it's parts.

Downloads last month
12
Safetensors
Model size
7.24B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for jeiku/Rosa_v2_7B

Merges
1 model
Quantizations
3 models