On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes Paper • 2306.13649 • Published Jun 23, 2023 • 37
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch50-lr0.1-val64-taskwise 2B • Updated Jun 12 • 3
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch50-lr0.1-val64-taskwise 2B • Updated Jun 12 • 3
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch50-lr0.1-val64-layerwise 2B • Updated Jun 10 • 3
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch50-lr0.1-val64-layerwise 2B • Updated Jun 10 • 3
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch50-lr0.1-val64 2B • Updated May 18 • 5
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch20-lr0.1-val64 2B • Updated May 25 • 1
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch20-lr0.1-val64 2B • Updated May 25 • 1
vohuutridung/cnn_arxiv_mediasum-sequential_efficient-qwen3-1.7b-epoch1-lr0.1-val64 2B • Updated May 25 • 1