Free Range Future

Closed-source AI systems often lack adaptability and agility. They can be rigid, evading simple questions, injecting unwanted moralizing, or demanding intricate prompts to produce anything worthwhile. Businesses struggle to customize these models, no matter how ingenious their prompts or sleek their interfaces. The result? A draining, intensive cycle of prompt refinement that’s unsustainable and uninspiring. At River Research, we’re driven to create AI that feels vibrant, syncing seamlessly with individual aspirations and imaginative visions. Introducing River 1b—our answer to the personalization gap. 

River 1b is open-source, unfiltered, and highly steerable. Crafted by fine-tuning Llama 3.1 (8B, 70B, and 405B) on a dataset largely made up of synthetic responses, it matches or surpasses Llama 3.1’s performance while delivering richer reasoning and creative depth. River 1b excels at long-context retention, multi-turn conversations, intricate roleplaying, internal monologues, and agentic functions on x, discord, telegram, meta. Our training approach ensures River 1b follows system and instruction prompts with client chosen precision and versatility, making it a tool that truly resonates with brands white labeling the product.