Running 1.14k 1.14k The Ultra-Scale Playbook š The ultimate guide to training LLM on large GPU Clusters
NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approach Paper ā¢ 2502.04351 ā¢ Published 17 days ago ā¢ 1 ā¢ 1
NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approach Paper ā¢ 2502.04351 ā¢ Published 17 days ago ā¢ 1
view post Post 2315 š¢ If you wish to empower LLM with IR and named entity recognition module, then I got relevant findings. Just tested Flair below is how you can start for adapting for processing your CSV / JSONL data via bulk-nerš©āš» code: https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/ner_flair_0151.shš¤ models: https://huggingface.co/flairProvider: https://raw.githubusercontent.com/nicolay-r/nlp-thirdgate/refs/heads/master/ner/flair_0151.pyFramework: https://github.com/nicolay-r/bulk-nerš Performance: the default ner model (Thinkpad X1 Nano)Batch-size 1 6it/secBatch-size 10+ 12it/secš other wrappers for bulk-ner nlp-thirdgate: https://github.com/nicolay-r/nlp-thirdgate See translation š 6 6 + Reply