Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

NAS-PO-DAPO-Qwen3-VL-8B – AI Model by ANke121 | AlphaNeural AI

You can deploy this model and start earning money today!

ANke121/
NAS-PO-DAPO-Qwen3-VL-8B

like

0

image-text-to-text

vision-language

reinforcement-learning

PAPOGalaxy/PAPO_ViRL39K_train

Qwen/Qwen3-VL-8B-Instruct

endpoints_compatible

Views

No views yet

NAS-PO-DAPO-Qwen3-VL-8B

Qwen3-VL-8B-Instruct trained for 202 RLVR steps with DAPO and NAS-PO: Native Attention-Strategy Policy Optimization for Vision-Language Models.

NAS-PO adds trajectory-level NAS-AS advantage scaling and positive-anchored token-level AAC routing consolidation to the DAPO optimization backbone.

Training

Data: ViRL39K, 38,870 examples
Rollouts per prompt: 8
Rollout / actor global batch: 384 / 128
Maximum prompt / response: 4096 / 256 tokens
Sampling: temperature 1.0, top-p 0.99
AdamW bf16: learning rate 1e-6, weight decay 0.01
NAS-AS drop quantile: 0.25
AAC target loss ratio: 0.3
Reference-policy KL: disabled
Hardware: 8 NVIDIA H100 80 GB GPUs

Evaluation

The paper reports 67.94 overall mean Accuracy@8 over eight configurations from seven benchmarks. Accuracy@8 is mean response accuracy, not pass@8.

Usage

python

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

repo = "ANke121/NAS-PO-DAPO-Qwen3-VL-8B"
model = Qwen3VLForConditionalGeneration.from_pretrained(repo, torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(repo)

This is a research checkpoint. Outputs may be incorrect; verify them before consequential use. Citation metadata will be added after the paper is public.