Goliath 120B

Goliath 120B is an innovative large language model (LLM) developed by merging two distinct, fine-tuned Llama 70B models: Xwin and Euryale. This unique combination results in a robust 120B parameter model, offering advanced text generation capabilities. The merging process was facilitated by the 'mergekit' framework developed by @chargoddard, with crucial assistance from @Undi95 on merge ratios. Designed for optimal performance in conversational AI, Goliath 120B excels in chat applications, providing fluid and coherent responses. It supports streaming, ensuring a dynamic user experience. With a context window of 6,000 tokens and a maximum output of 4,000 tokens, it can handle complex interactions. Pricing is set at $3.75 per 1M input tokens and $7.50 per 1M output tokens, available on the PRO access tier. While powerful for text-based tasks, it's important to note that Goliath 120B does not support image generation. Its strengths lie in its ability to process and generate human-like text, making it a valuable asset for developers and businesses seeking advanced conversational AI solutions.