Mamba2InLlama3.2-3B Collection Mamba distilled from Llama3.2 3B Instruct. The Mamba in the Llama: Distilling and Accelerating Hybrid Models (https://arxiv.org/abs/2408.15237). • 4 items • Updated Nov 17
MambaInLlama-dpo Collection Directly distill from Llama, the finetune in DPO • 4 items • Updated Nov 17
MambaInLlama-distill Collection Directly distill from Llama without doing SFT and DPO • 4 items • Updated Nov 17
MambaInLlama-distill Collection Directly distill from Llama without doing SFT and DPO • 4 items • Updated Nov 17
Mamba2InLlama3.2-3B Collection Mamba distilled from Llama3.2 3B Instruct. The Mamba in the Llama: Distilling and Accelerating Hybrid Models (https://arxiv.org/abs/2408.15237). • 4 items • Updated Nov 17