🚀 「大模型」2小时从0训练65M参数的视觉多模态VLM！🌏 Train a 65M-parameter VLM from scratch in just 2h!

Go to file

jingyaogong 12906766fb Delete LICENSE		2024-09-16 10:50:50 +08:00
images	update readme	2024-09-16 10:47:15 +08:00
CODE_OF_CONDUCT.md	update readme	2024-09-16 10:47:15 +08:00
README.md	update readme	2024-09-16 10:47:15 +08:00
README_en.md	update readme	2024-09-16 10:47:15 +08:00

中文 | English

👉Train a visual multimodal VLM with a small number of parameters from scratch

🎉Expected to be open sourced within 2024, we are working tirelessly on coding and training!

License

This repository is licensed under the Apache-2.0 License.