Comment by kccqzy
8 months ago
It seems way worse than other small models, including responding with complete non sequiturs. I think my favorite small model is still DeepSeek distilled with Llama 8B.
8 months ago
It seems way worse than other small models, including responding with complete non sequiturs. I think my favorite small model is still DeepSeek distilled with Llama 8B.
The key here is multimodal.