OpenLLM-Ro/RoLlama3-8b-Instruct

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kTool Calling:SupportedPublished:Oct 9, 2024License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Warm

OpenLLM-Ro/RoLlama3-8b-Instruct is an 8 billion parameter instruction-tuned generative text model developed by OpenLLM-Ro, specialized for the Romanian language. Fine-tuned from Meta-Llama-3-8B-Instruct, this model is part of the first open-source effort to build a large language model specifically for Romanian. It excels in Romanian natural language tasks and is intended for assistant-like chat applications, demonstrating strong performance in Romanian-specific benchmarks.

Loading preview...

RoLlama3-8b-Instruct: A Specialized Romanian LLM

OpenLLM-Ro/RoLlama3-8b-Instruct is an 8 billion parameter instruction-tuned generative text model, developed by OpenLLM-Ro as part of the first open-source initiative to create large language models specifically for Romanian. This model is fine-tuned from Meta-Llama-3-8B-Instruct and is designed to handle a variety of natural language tasks in Romanian, particularly excelling in assistant-like chat scenarios.

Key Capabilities

  • Romanian Language Specialization: Developed and fine-tuned using a comprehensive suite of Romanian datasets, including RoAlpaca, RoDolly, and RoUltraChat, ensuring high proficiency in Romanian.
  • Instruction Following: Optimized for understanding and executing instructions, making it suitable for interactive applications.
  • Strong Benchmark Performance: Demonstrates competitive performance against its base model, Llama-3-8B-Instruct, in Romanian-specific benchmarks like MT-Bench and RoCulturaBench, often surpassing it in key metrics.

Intended Use Cases

  • Research in Romanian NLP: Ideal for academic and research purposes focused on the Romanian language.
  • Assistant-like Chatbots: Well-suited for developing conversational AI agents that interact in Romanian.
  • Natural Language Tasks: Can be adapted for various Romanian natural language processing tasks, including text generation and understanding.

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