Knowledgator Releases GLiFormer: A 575M-Parameter Encoder That Hits 91.10 F1 on Nested JSON Extraction Without Generating Tokens
Knowledgator released GLiFormer, an Apache-2.0 encoder (264M/575M) handling NER, classification, relations, and nested JSON extraction, scoring 91.10 F1.
Knowledgator Engineering released GLiFormer, a schema-conditioned encoder that performs NER, classification, relation extraction, nested JSON structuring, and embeddings without generating output tokens. GLiFormer Large v1 has 575.6M parameters and scores 91.10 F1 on nested JSON extraction, close to GPT-5.6-luna's 91.96; both checkpoints are Apache 2.0 on Hugging Face. Reported median latency is 69 ms on GPU for the base model, though relation extraction (21.33 micro-F1) still trails GLiNER-Relex and larger LLMs.
- Single encoder handles NER, classification, relations, nested JSON, and embeddings via runtime schemas
- Large checkpoint scores 91.10 F1 on nested JSON, near GPT-5.6-luna's 91.96
- Apache 2.0 weights install via pip and run on CPU or GPU with zero generated tokens
- Relation extraction trails GLiNER-Relex (25.6) and Gemma-4-31B-IT (25.08)
- Vendors
- KnowledgatorHugging Face
- Organizations
- Knowledgator
From the original article
4 min read at marktechpost.com
GLiFormer Large scores 91. 10 F1 on nested JSON, near GPT-5. 6-luna's 91.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.