---
license: other
license_name: lfm1.0
base_model: LiquidAI/LFM3-VL-2B
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- webbrain
- liquid
- lfm3
- lfm3-vl
- browser-agent
- decision-model
- webbrain-vld
- custom_code
---

# LFM3-VL-2B-VLD Multipass

`LiquidAI/LFM3-VL-2B` adapted with WebBrain's multipass **VL-D** (`verify` Yes/No per option + `readout` option code) decision protocol, distilled from `LiquidAI/d1-2B` on WebBrain multimodal browser workflow screenshots — **without full VL/Compass fine-tuning** (vision tower frozen, language backbone adapted via LoRA and merged to BF16).

## Companion Repositories

- [`webbrain-one/lfm3-vld-2b-multipass-onnx`](https://huggingface.co/webbrain-one/lfm3-vl-2b-vld-onnx): WebGPU ONNX bundle (`decoder_q8f16.onnx`, `decoder_q4f16.onnx` with `decision_hidden` exposed, `vision_encoder_fp16.onnx`, and trained linear decision probes).
- [`webbrain-one/lfm3-vld-2b-multipass-gguf`](https://huggingface.co/webbrain-one/lfm3-vl-2b-vld-gguf): GGUF exports (`BF16`, `Q8_0`, `Q4_K_M`, and `mmproj-F16`) for `llama.cpp` (`/v1/chat/completions` + `/v1/systemone`).
- [`webbrain-one/lfm3-vld-2b-multipass-lora`](https://huggingface.co/webbrain-one/lfm3-vl-2b-vld-lora): LoRA adapter (`r=32, alpha=64`) and projector weights.

## Results on d1 Balanced Browser Decision Benchmark (`final_test`, 126 Categorical Questions)

| Model / Protocol | Correct | Completions Found | False Completions | Unknown Recognized | Score MAE |
|---|---:|---:|---:|---:|---:|
| **LFM3-VLD-2B (`probe` / `probe-cs`)** | **126/126 (100.0%)** | **24/24** | **0/48** | **24/24** | **9.56e-8** |
| **LFM3-VLD-2B (`verify` zero-shot)** | **126/126 (100.0%)** | **24/24** | **0/48** | **24/24** | **4.11e-5** |
| **LFM3-VLD-2B (`readout`)** | **125/126 (99.2%)** | **24/24** | **0/48** | **24/24** | **0.0189** |
| Base `LiquidAI/LFM3-VL-2B` (`verify` zero-shot) | 106/126 (84.1%) | 24/24 | 0/48 | 4/24 | 0.0004 |
| Base `LiquidAI/LFM3-VL-2B` (`readout`) | 102/126 (81.0%) | 24/24 | 1/48 | 0/24 | 0.1106 |