RaguTeam/RAGU-lm
TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:Oct 18, 2025License:mitArchitecture:Transformer0.0K Open Weights Warm

RaguTeam/RAGU-lm is a 0.8 billion parameter Qwen-3-0.6B fine-tuned model, specifically designed for knowledge graph building in Russian. It excels at extracting, normalizing, and describing entities, as well as identifying relations between them from text. This model is optimized for semantic information extraction tasks, offering specialized capabilities for structured data generation.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p