[MASSIVE TINY RELEASE] - Supra2-Medium-Base - a tiny 25M parameters model competing heavily with our previous 50M model!
Hey guys! Supra2-Medium is finally out! It's a 25M parameters qwen3 architecture model trained entirely from scratch (on our new rig: RTX 5060 Ti 16GB + the new RTX 5060 8GB!). Here's how it competes in benchmarks with Supra-50M-Base (which is double as large!!): preview.redd.it/adlxzivwljkh1.png Note: This is a BASE model only; instruction tuned version maybe to come in the next time. Link to our HF org: huggingface.co/SupraLabs --> Link to the model: huggingface.co/SupraLabs/Supra2-Medium-Base <-- Here's a sample from the model: Artificial intelligence (AI) is espoused by the AI community. The AI community is a group of people who are interested in AI and are interested in the use of AI in the field of AI. The goal of AI is to improve the quality of life of people in the field. The aim of AI is the development of AI and the application of AI in a society. The purpose of AI is that it can be used to improve the performance of the society. It is a technology that is used to improve human intelligence. The technology is used to make the human intelligence.Artificial intelligence (AI) is espoused by the AI community. The AI community is a group of people who are interested in AI and are interested in the use of AI in the field of AI. The goal of AI is to improve the quality of life of people in the field. The aim of AI is the development of AI and the application of AI in a society. The purpose of AI is that it can be used to improve the performance of the society. It is a technology that is used to improve human intelligence. The technology is used to make the human intelligence. Give us a like and a follow and feel free to provide us with feedback! 🤗🔥 ...and...stay tuned: Supra3 coming soon with four models: Flash-Lite 25M, Flash 50M, Pro 75M and Ultra 100M. 👀