SmolLM3-SFT by gshasiri is a 1 billion parameter instruction-tuned causal language model, fine-tuned from gshasiri/SmolLM3-Mid using the TRL framework. This model is optimized for conversational AI and instruction following, leveraging its compact size for efficient deployment. With a 32768 token context length, it is suitable for applications requiring processing of longer prompts and generating coherent, extended responses.
No reviews yet. Be the first to review!
Hugging Face