Modelpublic

lucas-vitrus/liquid-crow

sourceHugging Facecc-by-nc-4.0updated 2mo agoView on Hugging Face

1likes109downloads

Model Card

Liquid Crow

![Liquid Crow by Vitrus](https://www.vitrus.com/news/micro-world-models-1)

A small brain. Intelligent. Always observing.

Liquid Crow is a compact visual brain designed to stay close to the world it watches: small enough to live beside physical agents, intelligent enough to turn a camera frame into useful context, and always observing so the system can understand what changes next.

Live camera demo · Research note · Vitrus

System

text

camera frame → image processor → vision projector → compact VLM → world description
                                        │
                         LoRA · ONNX · ONNX Q4 · GGUF

This repository is the single public release point for Liquid Crow: the model adapter, deployment formats, processor configuration, integrity manifests, code examples, and media.

Example

[image]

Repository layout

Path	Contents
`lora/`	PEFT LoRA adapter and processor files
`onnx/model.onnx`	FP16 ONNX forward-logits graph
`onnx/model-q4.onnx`	ONNX Runtime weight-only 4-bit graph
`gguf/`	Q4KM language model and FP16 vision projector
`transformers/`	tokenizer, processor, chat template, and model configuration
`examples/`	LoRA, ONNX Runtime, and llama.cpp examples
`media/`	cover image and animated example
`RELEASE_MANIFEST.json`	sizes and SHA-256 hashes for the primary artifacts

Quick start: LoRA

bash

pip install torch transformers peft pillow huggingface_hub
python examples/load_lora.py path/to/image.jpg

The example downloads the Liquid Crow adapter from this repository and applies it to LiquidAI/LFM2.5-VL-450M-Extract.

Quick start: GGUF

bash

hf download lucas-vitrus/liquid-crow \
  gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-Q4_K_M.gguf \
  gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-mmproj-f16.gguf \
  --local-dir ./liquid-crow

llama-server \
  -m ./liquid-crow/gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-Q4_K_M.gguf \
  --mmproj ./liquid-crow/gguf/LFM2.5-VL-450M-reasoning-tracing-step2000-mmproj-f16.gguf \
  -c 1024 --image-min-tokens 64 --image-max-tokens 256

Quick start: ONNX Runtime

bash

pip install onnxruntime transformers torch pillow huggingface_hub
python examples/onnx_forward.py path/to/image.jpg --quantized

The ONNX files expose a multimodal forward-logits graph. Autoregressive generation remains the responsibility of the consuming runtime. The quantized graph requires ONNX Runtime support for com.microsoft::MatMulNBits.

Runtime notes

—Both GGUF files are required for visual inference.
—The LoRA adapter requires the base model.
—lora/ contains the final adapter; the ONNX and GGUF deployment exports use the selected step-2,000 checkpoint.
—onnx/model-q4.onnx quantizes eligible matrix weights; other operations retain their exported precision.
—See SHA256SUMS and export_manifest.json for artifact integrity and interface details.

License

Liquid Crow is released under the Creative Commons Attribution-NonCommercial 4.0 International license. Commercial use is not permitted without separate written permission from Vitrus.

The underlying base model and any third-party components remain subject to their respective upstream terms. You must comply with all applicable licenses; where terms differ, the more restrictive terms apply.