1. h2oGPT: A large language model built by H2O.ai that can handle a wide range of tasks and domains. It has 12B - 20B parameters and can process 256 - 2048 tokens of input context. It is licensed under Apache 2.0, which means you can use it for free and modify it as you wish. 😍
2. MPT-7B: A commercially usable large language model that can generate high-quality natural language texts. It has 7B parameters and was trained on a curated dataset of 84k documents (ALiBi). It is also licensed under Apache 2.0 and CC BY-SA-3.0, which means you can use it for both personal and commercial purposes. 🤩
3. RedPajama-INCITE: A family of models that includes a base model, an instruction-tuned model, and a chat model. They have 3B - 7B parameters and can process 2048 tokens of input context. They are also licensed under Apache 2.0, which means you can use them for any purpose. 😎
4. OpenLLaMA: An open reproduction of LLaMA, a large language model that can learn from multiple modalities such as text, images, and audio. It has 3B and 7B parameter versions and can process 2048 tokens of input context. It is also licensed under Apache 2.0, which means you can use it for any purpose. 🤗
5. Falcon: A mysterious large language model that has not been fully revealed yet, but promises to be state-of-the-art. It has 7B and 40B parameter versions and can process 2048 tokens of input context. It is also licensed under Apache 2.0, which means you can use it for any purpose. 🧐
Comments
Post a Comment
"Welcome to my blog, where I, Sandeep Giri, share my passion for the Tech World. Join me on an exciting journey as we explore the latest trends, innovations, and advancements in the world of technology."