Sao10K: Llama 3 Stheno 8B v3.3 32K

Stheno 8B 32K is a creative writing/roleplay model from Sao10k(opens in new tab). It was trained at 8K context, then expanded to 32K context.

Compared to older Stheno version, this model is trained on:

• 2x the amount of creative writing samples
• Cleaned up roleplaying samples
• Fewer low quality samples