The ahmedheakl/cass-sm4090-3b model is a 3.1 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-Coder-3B-Instruct. It was trained on specific CUDA and AMD datasets, suggesting an optimization for code-related tasks, particularly those involving GPU architectures. This model is designed for applications requiring a compact yet capable code-focused LLM.
No reviews yet. Be the first to review!