Please following paper's format to use this model.
input: SPRiNGSと最も仲の良いライバルグループ。 <社会><文芸><学問><技術><自然> 固有表現抽出
output: <社会>固有表現抽出:その他の組織名;SPRiNGS
generated_ids = model.generate(inputs, max_new_tokens=2000) #Don't need any other set, just max new tokens.
paper cite: https://arxiv.org/abs/2311.06838
bib: @misc{gan2023giellm, title={GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect}, author={Chengguang Gan and Qinghao Zhang and Tatsunori Mori}, year={2023}, eprint={2311.06838}, archivePrefix={arXiv}, primaryClass={cs.CL} }
- Downloads last month
- 12
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.