Thinking Machines releases Inkling 2 Small's weights under Apache 2.0
TL;DR
- On 12 November Thinking Machines Lab put Inkling 2 Small's weights on Hugging Face under an Apache 2.0 licence, a week after the model's launch.
- The main NVFP4 checkpoint needs a GPU cluster with at least 500GB of VRAM, and the MXFP8 checkpoint needs at least 800GB.
- Transformers v5.23.0 added the architecture on 13 November, and the model card names seven inference providers.
Read the full story
Sign in with your email to read AI News. It’s free.