@maximelabonne: Train encoders today like it's 2020 again!
Summary
Liquid AI fine-tuned their LFM2.5-Encoder models (230M and 350M) to perform multi-label classification in a single forward pass, eliminating the need for decoding loops or parsing. This demonstrates efficient label scoring for NLP tasks.
View Cached Full Text
Cached at: 07/30/26, 03:49 AM
Train encoders today like it’s 2020 again!
Liquid AI (@liquidai): Multi-label classification. One forward pass. Zero completion tokens.
We fine-tuned LFM2.5-Encoder-230M and LFM2.5-Encoder-350M to score every label at once: no decoding loop, nothing to parse or repair. First in a new encoder demo series, watch it in action.
Check out the
Similar Articles
@maximelabonne: We just released two new encoder models (MLM) in 2026 They're super fast, easy to train, and strongly multilingual. Try…
Liquid AI released two new encoder models, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, that are fast, easy to train, and strongly multilingual, with speed benchmarks showing over 3.7x improvement on CPU compared to ModernBERT-base.
@vivmarquez: Not every AI problem is a generation problem. For routing, classification, retrieval, policy checks, and similar tasks,…
Liquid AI releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, bidirectional encoders optimized for non-generative tasks like classification and retrieval, offering fast CPU inference at long context.
LFM2.5-Encoders for Fast Long-Context Inference on CPU
Liquid AI releases LFM2.5-Encoders (230M and 350M), efficient encoder models optimized for long-context inference on CPU, matching or beating larger encoders on benchmarks with 3.7x speedup over ModernBERT-base.
LiquidAI/LFM2.5-Embedding-350M
Liquid AI releases LFM2.5-Embedding-350M, a dense bi-encoder for multilingual retrieval supporting 11 languages, as a drop-in replacement for RAG pipelines.
LiquidAI/LFM2.5-ColBERT-350M
LiquidAI releases LFM2.5-ColBERT-350M, a late-interaction multilingual retrieval model, along with a dense bi-encoder variant, both built on LFM2.5-350M-Base, supporting 11 languages and designed as drop-in replacements for RAG pipelines.