LFM2.5-Encoder-350M

Specifications

Property	Value
Parameters	~354M
Type	Bidirectional encoder
Hidden Size	1024
Vocabulary Size	65,536
Context Length	8,192 tokens
Supported Languages	English, German, Spanish, French, Italian, Dutch, Polish, Portuguese, Arabic, Hindi, Japanese, Russian, Turkish, Vietnamese, Chinese (15)

Text Classification

Sentiment, topic, intent/routing, moderation, and business-text linting.

Token Classification

Named-entity recognition, span extraction, and sequence labeling.

Fine-Tuning Backbone

A base for dense embedding or late-interaction retrievers, NLI, and semantic similarity.

Quick Start

This is a base encoder that produces general-purpose representations. For task outputs, fine-tune it with a task head for your use case. See the fine-tuning overview to get started.

Transformers

Install:

pip install -U transformers

Run masked-token prediction:

from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-Encoder-350M", trust_remote_code=True)
mlm = AutoModelForMaskedLM.from_pretrained("LiquidAI/LFM2.5-Encoder-350M", trust_remote_code=True)

text = f"The capital of France is {tok.mask_token}."
enc = tok(text, return_tensors="pt")
with torch.no_grad():
    logits = mlm(**enc).logits
pos = (enc["input_ids"][0] == tok.mask_token_id).nonzero()[0].item()
print([tok.decode([t]).strip() for t in logits[0, pos].topk(5).indices.tolist()])
# -> ['Paris', 'Strasbourg', 'Paris', 'Lyon', 'Versailles']

Load the encoder body for downstream tasks:For classification, token classification, regression, or retrieval, load the encoder body and attach your own head:

from transformers import AutoModel

body = AutoModel.from_pretrained("LiquidAI/LFM2.5-Encoder-350M", trust_remote_code=True)

Models

Fine-tuning

Edge Inference

GPU Inference

Cloud Inference

Guides

Help

Specifications

Text Classification

Token Classification

Fine-Tuning Backbone

Quick Start

​Specifications

Text Classification

Token Classification

Fine-Tuning Backbone

​Quick Start

Specifications

Quick Start