See merge.yml for information about this model's contents.

In some brief testing, this model performed very well in RP and general chatting, easily better than v1, and about as good as I could hope for from the StableLM lineage. This will likely be my final StableLM merge.

FP16 can be found here: https://huggingface.co/jeiku/Rosa_v2_3B

Downloads last month
25
GGUF
Model size
2.8B params
Architecture
stablelm
Hardware compatibility
Log In to view the estimation

2-bit

3-bit

4-bit

5-bit

6-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support