Qwen3.5-2B-MLP is an open-weight model from Zhuoming Liu, released under Apache License 2.0. Its published files total 397.4 MB.
Inference checkpoint for Memory as Weights: Internalizing Long-Term History for Streaming Videos. Evaluation requires the MaLoW code release. The code has been prepared locally; public GitHub publication is pending. Intended repository: MaLoW (forthcoming).
Model Card
By Zhuoming Liu, published under apache-2.0, revision 3e72da605c6a.
Inference checkpoint for Memory as Weights: Internalizing Long-Term History for Streaming Videos. Evaluation requires the MaLoW code release. The code has been prepared locally; public GitHub publication is pending. Intended repository: MaLoW (forthcoming). Download the base model separately: Qwen/Qwen3.5-2B. This repository contains inference modules, not a standalone base model. Follow docs/vlaevaluation.md in the MaLoW code release for Simpler WidowX. Reported reference success rates (not a fresh evaluation of this export): datasetstatistics.json supplies action normalization; use the oxebridge key for WidowX. The action-head tensor dictionary uses PyTorch's restricted weightsonly=True…
Read Zhuoming Liu's full model card
Q3.5-2B-MLP
Inference checkpoint for Memory as Weights: Internalizing Long-Term History for Streaming Videos.
Evaluation requires the MaLoW code release. The code has been prepared locally; public GitHub publication is pending. Intended repository: MaLoW (forthcoming).
Download the base model separately: Qwen/Qwen3.5-2B. This repository contains inference modules, not a standalone base model.
Follow docs/vla_evaluation.md in the MaLoW code release for Simpler WidowX.
Reported reference success rates (not a fresh evaluation of this export):
| Stack green block | Carrot on plate | Spoon on towel | Eggplant in basket | Overall |
|---|---|---|---|---|
| 0.208 | 0.75 | 0.708 | 0.708 | 0.5937 |
dataset_statistics.json supplies action normalization; use the oxe_bridge key for WidowX. The action-head tensor dictionary uses PyTorch's restricted weights_only=True loader.
Weights and inference metadata are distributed under Apache-2.0. See LICENSE and NOTICE; base models and benchmark assets retain their respective upstream terms.
Identity and Version
- Repository
- zhuomingliu/Qwen3.5-2B-MLP
- Publisher
- Zhuoming Liu
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 3e72da605c6af685ffbf7a42bc02b8a3fa76e0d1
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
18 files, 397.4 MB in total. The weights are 2 files totalling 377.3 MB in pt, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| vla_qwen_lora_adapter/adapter_model.safetensors | Weights | 374.2 MB | 698cdcd094cb |
| vla_trainable_params.pt | Weights | 3.2 MB | 07b5d88e8f76 |
| dataset_statistics.json | Configuration | 5.9 KB | — |
| processor_config.json | Configuration | 1.2 KB | — |
| release_manifest.json | Configuration | 2.7 KB | — |
| vla_config.json | Configuration | 1.4 KB | — |
| vla_qwen_lora_adapter/adapter_config.json | Configuration | 1.2 KB | — |
| LICENSE | Documentation | 11.3 KB | — |
| NOTICE | Documentation | 1.3 KB | — |
| README.md | Documentation | 1.2 KB | — |
| LICENSES/SimplerEnv-MIT.txt | Other | 1.1 KB | — |
| LICENSES/StreamingBench-MIT.txt | Other | 1.1 KB | — |
| LICENSES/doc-to-lora-MIT.txt | Other | 1.1 KB | — |
| SHA256SUMS | Other | 1.4 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 6f32ce20dc35 |
| tokenizer_config.json | Tokenizer | 1.2 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 377.3 MB
Released by Zhuoming Liu through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.5-2B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 377.3 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3.5-2B-MLP
Can I use Qwen3.5-2B-MLP commercially?
Yes. Qwen3.5-2B-MLP is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.