Views
No views yet
1config.json
2latentskill_pretrain_qwen3_8b/
3 pretrain.tar.gz
4latentskill_sft_qwen3_8b/
5 train.tar.gz1checkpoints/latentskill_pretrain_qwen3_8b/pretrain/
2checkpoints/latentskill_sft_qwen3_8b/train/1hf download AofaYu71/LatentSkill \
2 --repo-type model \
3 --local-dir checkpoints \
4 --include "config.json" \
5 "latentskill_pretrain_qwen3_8b/pretrain.tar.gz" \
6 "latentskill_sft_qwen3_8b/train.tar.gz"
7
8tar -xzf checkpoints/latentskill_pretrain_qwen3_8b/pretrain.tar.gz \
9 -C checkpoints/latentskill_pretrain_qwen3_8b/
10
11tar -xzf checkpoints/latentskill_sft_qwen3_8b/train.tar.gz \
12 -C checkpoints/latentskill_sft_qwen3_8b/config.json metadata file so Hugging Face can count model downloads through the model download-statistics query file. The file is included in the download command above and is not used as a standalone Transformers runtime configuration.1@article{yu2026latentskillincontexttextualskills,
2 title={LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents},
3 author={Aofan Yu and Chenyu Zhou and Tianyi Xu and Zihan Guo and Rong Shan and Zhihui Fu and Jun Wang and Weiwen Liu and Yong Yu and Weinan Zhang and Jianghao Lin},
4 year={2026},
5 eprint={2606.06087},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2606.06087},
9}