arcee-ai/Arcee-Nova
Arcee-Nova is a 72.7 billion parameter instruction-tuned language model developed by arcee-ai, based on a merge of Qwen2-72B-Instruct with a custom generalist dataset. It features a 131,072 token context length and is optimized for a wide range of tasks including reasoning, creative writing, and coding. Evaluated on the OpenLLM Leaderboard 2.0 stack, it demonstrates performance approaching that of GPT-4 (May 2023).
Loading preview...
Arcee-Nova: High-Performance Open Source LLM
Arcee-Nova is arcee-ai's leading open-source language model, built by merging Qwen2-72B-Instruct with a custom model fine-tuned on a generalist dataset mixture. With 72.7 billion parameters and a substantial 131,072 token context length, it is designed for advanced language understanding and generation.
Key Capabilities
- Reasoning: Excels at complex problem-solving and logical inference.
- Creative Writing: Generates original and engaging content across diverse genres.
- Coding: Supports programming tasks, including code generation and debugging.
- General Language Understanding: Comprehends and produces human-like text effectively.
Performance and Evaluation
Arcee-Nova has been rigorously evaluated on the same stack as the OpenLLM Leaderboard 2.0, where it stands as a top-performing open-source model. Its performance metrics indicate capabilities that rival those of GPT-4 from May 2023, showcasing its strength across various benchmarks.
Good For
- Business Applications: Ideal for customer service chatbots, automated content creation, and accelerating software development workflows.
- Research & Development: Useful for data analysis, literature reviews, and hypothesis generation.
- Educational Tools: Can power adaptive learning systems and intelligent tutoring programs.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.