alpha-sys-1-1.6B-260919: the weights of LiquidAI/LFM2.5-VL-1.6B with a LoRA (rank 32, every linear
layer of the language model and the projector) trained on seven public environments and merged in.
The vision tower is unchanged. Training configuration in run.json. Changed file: model.safetensors.
Base model licensed under the LFM Open License v1.0 (LICENSE), whose terms apply to this derivative.