IIC/RigoChat-7b-v2
IIC/RigoChat-7b-v2 is a 7.6 billion parameter Qwen-2.5-based causal language model developed by Instituto de Ingeniería del Conocimiento (IIC). It is specifically fine-tuned using Direct Preference Optimization (DPO) for enhanced performance in Spanish language tasks, particularly excelling in generalist tasks and Retriever Augmented Generation (RAG) systems with Spanish databases by reducing hallucinations. The model supports a 131072 token context length and is optimized for various NLP tasks including Tool Use, Summarization, Math, Code, and Abstractive-QA in Spanish.
Loading preview...
RigoChat-7b-v2: Spanish-Optimized LLM
RigoChat-7b-v2 is the second iteration of a Large Language Model (LLM) family developed by Instituto de Ingeniería del Conocimiento (IIC), built upon the Qwen-2.5-7B-Instruct architecture. This 7.6 billion parameter model is specifically fine-tuned using Direct Preference Optimization (DPO) to deliver superior performance for Spanish language queries and tasks. A key focus of its training was to improve responses in RAG (Retriever Augmented Generation) systems with Spanish databases, aiming to prevent hallucinations and ensure safer, more accurate outputs.
Key Capabilities & Features
- Spanish Language Specialization: Optimized for a wide range of NLP tasks with Spanish instructions, including Tool Use, Summarization, Math, Code, and Abstractive-QA.
- Enhanced RAG Performance: Demonstrates improved safety and reduced hallucinations when integrated into RAG systems utilizing Spanish texts.
- Resource-Efficient Training: Achieved its current state in 8.5 hours on a single A100 GPU, leveraging a high-quality dataset and LoRA for memory optimization.
- Competitive Benchmarking: Outperforms several state-of-the-art models, including GPT-4o and Meta-Llama-3.1-8B-Instruct, in specific Spanish RAG-focused evaluation tasks (e.g., AQuAS, RagQuAS, CAM, Shops, Insurance).
Ideal Use Cases
- General Chatbot in Spanish: Functions effectively as a general conversational agent.
- Spanish RAG Systems: Highly recommended for applications requiring accurate information retrieval and generation from Spanish databases.
- Tool Use & Function Calling: Capable of integrating with external tools for enhanced functionality.
- Resource-Constrained Environments: Designed to be usable on hardware with reduced computational capacity, with a GGUF version available for further optimization.