Groq has recently released two innovative open-source models for tool use: Llama-3-Groq-70B-Tool-Use and Llama-3-Groq-8B-Tool-Use. These models are developed in collaboration with Glaive and designed to advance tool use and function-calling capabilities in AI.
The Llama-3-Groq-70B-Tool-Use model is the highest-performing model on the Berkeley Function Calling Leaderboard (BFCL), outperforming all other open-source and proprietary models. Achieving an impressive 90.76% overall accuracy has set a new benchmark in the field. Similarly, the Llama-3-Groq-8B-Tool-Use model has also demonstrated remarkable performance with an 89.06% overall accuracy, securing the third position on the BFCL. These models are now available on the GroqCloud Developer Hub and Hugging Face under the same permissive style license as the original Llama-3 models.
The development of these models involved a meticulous training approach that combined full fine-tuning and Direct Preference Optimization (DPO). Notably, no user data was used in the training process; instead, the models were trained using ethically generated data. This approach ensures that the models are high-performing and align with ethical standards in AI development. The training process also included a thorough contamination analysis using the LMSYS method. This resulted in a low contamination rate of just 5.6% for the SFT data and 1.3% for the DPO data, indicating minimal overfitting on the evaluation benchmark.
In addition to their specialized tool use capabilities, the Llama-3 Groq Tool Use models are recommended for use in a hybrid approach with general-purpose language models. This strategy involves implementing a routing system that analyzes incoming user queries to determine the most appropriate model for each request. For queries involving function calling, API interactions, or structured data manipulation, the Llama-3 Groq Tool Use models are utilized. For general knowledge, open-ended conversations, or tasks not specifically related to tool use, a general-purpose language model like the unmodified Llama-3 70B is recommended. This approach ensures that each query is handled by the most suitable model, maximizing the overall performance and capabilities of the AI system.
Both Llama-3-Groq-70B-Tool-Use and Llama-3-Groq-8B-Tool-Use are available for preview access through the Groq API, with model IDs llama3-groq-70b-8192-tool-use-preview and llama3-groq-8b-8192-tool-use-preview, respectively. Groq encourages the community to start building and experimenting with these models through the GroqCloud Developer Hub, paving the way for future innovations in AI tool use.
In conclusion, Groq introduced the Llama-3-Groq-Tool-Use models with their state-of-the-art performance and permissive licensing. These models are poised to impact AI research and development substantially. Groq’s commitment to ethical AI development and its collaborative approach with the community underscore the company’s leadership in the field.
The post Groq Releases Llama-3-Groq-70B-Tool-Use and Llama-3-Groq-8B-Tool-Use: Open-Source, State-of-the-Art Models Achieving Over 90% Accuracy on Berkeley Function Calling Leaderboard appeared first on MarkTechPost.
#AIShorts #Applications #ArtificialIntelligence #EditorsPick #LanguageModel #LargeLanguageModel #Staff #TechNews #Technology [Source: AI Techpark]