{"id":"2305.18239","title":"A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models","url":"https://codeofpaper.com/paper/2305.18239","arxiv_url":"https://arxiv.org/abs/2305.18239","published":"2023-05-26","code":"community","best":{"full_name":"huggingface/transformers","url":"https://github.com/huggingface/transformers","tier":"high_confidence_community","stars":162097,"license":"Apache-2.0","framework":"PyTorch","language":"Python","last_commit":"2026-04-30T07:55:38"},"most_starred_community":null,"implementations":[{"full_name":"huggingface/transformers","url":"https://github.com/huggingface/transformers","tier":"high_confidence_community","stars":162097,"license":"Apache-2.0","framework":"PyTorch","language":"Python","last_commit":"2026-04-30T07:55:38"}],"possible_matches":0}