| Independent Core AI conversion of LiquidAI/d1-3B for text and image decisions. |
| Upstream: https://huggingface.co/LiquidAI/d1-3B |
| Revision: 051bcc464b01b9f92942b364d9586b0ef5912432 |
|
|
| The upstream checkpoint, upstream code and converted weights are governed by the |
| LFM Open License v1.0. A copy of the license accompanies this distribution. |
| Each bundle's checkpoint folder redistributes the upstream code, tokenizer, |
| configuration and license files unmodified, and the token embeddings, |
| multimodal projector and vision position table from the upstream weights. |
|
|
| The conversion uses 1x1 convolution projections, activation scaling, |
| tanh-form SiLU and a split FFN. The language backbone and SigLIP2 vision tower |
| are exported as FP16 Core AI assets for the Apple Neural Engine. Tokenization, |
| image preprocessing, token-embedding lookup, the FP32 multimodal projector, |
| and option readout run on the host CPU. The model has not been retrained. |
| This project is not affiliated with or endorsed by Liquid AI. |
| |
