GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zlab-princeton
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
zlab-princeton
Model Tree
Qwen/Qwen3.5-9B-Base
Input Modalities
Output Modalities
Supported Functionality
| Model | HF repo | Base model | Params |
|---|---|---|---|
Vero-Qwen3I-8B | zlab-princeton/Vero-Qwen3I-8B | Qwen3-VL-8B-Instruct | 8B |
Vero-Qwen3T-8B | zlab-princeton/Vero-Qwen3T-8B | Qwen3-VL-8B-Thinking | 8B |
Vero-MiMo-7B | zlab-princeton/Vero-MiMo-7B | MiMo-VL-7B-SFT-2508 | 7B |
Vero-Qwen25-7B | zlab-princeton/Vero-Qwen25-7B | Qwen2.5-VL-7B-Instruct | 7B |
Vero-600K dataset.VeroEval, a 30-benchmark suite for general visual reasoning.Example for zlab-princeton/Vero-Qwen35-9B-Base:
python
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGenerationfrom qwen_vl_utils import process_vision_info model_path = "zlab-princeton/Vero-Qwen35-9B-Base" model = Qwen2_5_VLForConditionalGeneration.from_pretrained( model_path, torch_dtype="auto", device_map="auto",)processor = AutoProcessor.from_pretrained(model_path) messages = [ { "role": "user", "content": [ {"type": "image", "image": "path/to/image.jpg"}, {"type": "text", "text": "What is the x axis value with the largest population?"}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs = process_vision_info(messages)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt",).to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=2048)output = processor.batch_decode( generated_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True,)[0]print(output)Vero models generate a reasoning trace in <think> tags followed by a final answer in <answer> tags. For downstream use, parse the final response from <answer>.
Recommended sampling parameters, following the Qwen3.5 defaults:
temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0, max_new_tokens=16384.bibtex
@misc{sarch2026vero, title={Vero: An Open RL Recipe for General Visual Reasoning}, author={Sarch, Gabriel and Cai, Linrong and Wang, Qunzhong and Wu, Haoyang and Chen, Danqi and Liu, Zhuang}, year={2026}}Vero is released under the Apache-2.0 license. Users should also review the licenses and usage terms of the underlying base models and any upstream datasets.
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGenerationfrom qwen_vl_utils import process_vision_info model_path = "zlab-princeton/Vero-Qwen35-9B-Base" model = Qwen2_5_VLForConditionalGeneration.from_pretrained( model_path, torch_dtype="auto", device_map="auto",)processor = AutoProcessor.from_pretrained(model_path) messages = [ { "role": "user", "content": [ {"type": "image", "image": "path/to/image.jpg"}, {"type": "text", "text": "What is the x axis value with the largest population?"}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs = process_vision_info(messages)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt",).to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=2048)output = processor.batch_decode( generated_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True,)[0]print(output)@misc{sarch2026vero, title={Vero: An Open RL Recipe for General Visual Reasoning}, author={Sarch, Gabriel and Cai, Linrong and Wang, Qunzhong and Wu, Haoyang and Chen, Danqi and Liu, Zhuang}, year={2026}}