GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
HughieHu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
HughieHu
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
text
model-00001-of-00012.safetensors … the fine-tuned weights (bf16), the model evaluated in the paperadapter/ the same fine-tune as a LoRA adapter on Qwen/Qwen3.6-27BThe root holds the base model with the LoRA adapter merged in, so it serves like any Qwen3.6-27B
checkpoint. adapter/ holds the adapter alone (rank 32, alpha 64, all linear layers of the language
model), for loading on top of the base model with PEFT or for further training.
Serve the model with any OpenAI-compatible server (vLLM, SGLang, …) with a 131,072-token context,
and run the harness from github.com/StarTrail-org/DRPixel
(eval/) against it. The paper's runs used the sampling settings below; the harness passes them
through when they are set.
bash
MODEL_NAME=HughieHu/DR-Pixel-TrainedMODEL_BASE_URL=http://localhost:8000/v1MODEL_API_KEY=EMPTYMODEL_TEMPERATURE=0.6 MODEL_TOP_P=0.95 MODEL_TOP_K=20 MODEL_PRESENCE_PENALTY=1.0SEARCH_URL=https://drpixel--drpixel-search-gate.us-east.modal.run # hosted page search python -m drbench.eval --config PageLoRA on all linear layers of the language model, one epoch at learning rate 1e-4 with an effective
batch size of 16 and a maximum length of 131,072 tokens, with per-step loss weights from
counterfactual credit and a constant weight of 1.5 on the final answer.
train/README.md describes the method
and the full recipe.
The weights are released under Apache 2.0, the license of the base model. The training data are trajectories generated by GPT-5.4 and remain subject to the terms of that model.
bibtex
@misc{hu2026drpixel, title = {DR Pixel: Page-Native Deep Research with Vision-Language Models}, author = {Hu, Tiansheng and Wang, Yichuan and Talwar, James V. and Tomlin, Nicholas and Zhao, Chen and Min, Sewon}, year = {2026}}@misc{hu2026drpixel, title = {DR Pixel: Page-Native Deep Research with Vision-Language Models}, author = {Hu, Tiansheng and Wang, Yichuan and Talwar, James V. and Tomlin, Nicholas and Zhao, Chen and Min, Sewon}, year = {2026}}