Large language models and APIs.

meta-llama/CodeLlama-7B-Instruct-hf is a 7 billion parameter instruction-tuned AI model developed by Meta, designed to assist with code generation, completion, and understanding across multiple programming languages with high efficiency and accuracy.

InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning.

Aya Expanse 8B is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained Command family of models with the result of a year’s dedicated research from Cohere For AI, including data arbitrage, multilingual preference training, safety tuning, and model merging. The result is a powerful multilingual large language model.

The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-Nemo-Base-2407. Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

HuggingFaceTB/SmolLM2-1.7B-Instruct is a 1.7 billion parameter instruction-tuned AI language model designed to provide efficient and accurate responses for a wide range of tasks while maintaining a lightweight and accessible architecture.

mistralai/Mathstral-7B-v0.1 is a 7 billion parameter AI model optimized for mathematical reasoning and problem-solving, designed to deliver precise and efficient solutions across a variety of mathematical domains.

deepseek-ai/deepseek-math-7b-instruct is a 7 billion parameter AI model specifically designed to excel in mathematical reasoning and problem-solving tasks, providing accurate and detailed step-by-step solutions.

microsoft/Phi-3.5-mini-instruct is a lightweight AI language model optimized for instruction-based tasks, offering efficient performance and high-quality responses with a compact architecture.

Qwen/Qwen2.5-3B-Instruct is a powerful 3 billion parameter AI language model designed to deliver high-quality, human-like responses across a wide range of natural language processing tasks.

Qwen/Qwen2.5-0.5B-Instruct is a compact 500 million parameter AI language model optimized for generating human-like responses and assisting with various natural language understanding tasks.

Qwen/Qwen2.5-1.5B-Instruct is a 1.5 billion parameter AI language model designed to generate human-like responses based on user inputs.

Qwen2-7B-Instruct is a versatile large language model with 7 billion parameters, optimized for instruction-following tasks. It delivers high performance in natural language understanding, content generation, and complex reasoning, making it ideal for a wide range of AI-driven applications, from chatbots to educational tools.

Qwen2.5-Math-7B-Instruct is a large language model with 7 billion parameters, specialized in advanced mathematical problem-solving and reasoning. It is fine-tuned for instruction-based tasks and excels in fields like algebra, calculus, and quantitative analysis, making it suitable for research, education, and technical applications.

Qwen2.5-Math-1.5B-Instruct is a math-specialized large language model with 1.5 billion parameters, fine-tuned for solving complex mathematical problems and handling instruction-based tasks. It excels in areas like algebra, calculus, and numerical reasoning, making it ideal for educational tools and research applications.

Qwen2.5-Coder-7B-Instruct is a specialized large language model with 7 billion parameters, designed for code understanding and generation. Fine-tuned for instruction-based tasks, it supports multiple programming languages, making it ideal for coding assistance, code completion, and educational applications.

Qwen1.5-0.5B-Chat is a lightweight conversational AI model with 500 million parameters, designed for efficient and interactive chat-based applications. Despite its smaller size, it offers fast performance and reliable natural language understanding, making it ideal for real-time AI interactions on resource-constrained systems.

PHI-4 by Microsoft is an advanced large language model designed for precise natural language understanding and generation. It offers robust performance in complex conversational AI and NLP tasks, making it well-suited for enterprise and research applications.

Qwen2.5-Coder-32B-Instruct is a powerful code-focused large language model with 32 billion parameters, fine-tuned for coding and instruction-based tasks. It excels in code generation, code completion, and understanding complex programming instructions across multiple languages.

Gemma-2-2B is a compact large language model by Google, featuring 2 billion parameters and optimized for instruction-based and multilingual tasks. It provides efficient natural language processing, making it suitable for a variety of AI-driven applications with lower computational requirements.

Gemma-2-9B is an advanced large language model by Google, featuring 9 billion parameters and designed for multilingual and instruction-following tasks. It delivers high-quality performance in complex natural language understanding and generation across various domains.