GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
microsoft
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
microsoft
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
We introduce X-Reasoner, a vision-language model posttrained solely on general-domain text for generalizable reasoning, using a twostage approach: an initial supervised fine-tuning phase with distilled long chainof-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-theart models trained with in-domain and multimodal data across various general and medical benchmarks. More details can be found in the paper: X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
We recommend installing the transformers version used in our experiments and other dependencies with this command:
text
pip install transformers==4.57.1 accelerate==1.12.0 torchvision==0.24.1 qwen-vl-utils==0.0.14Below, we provide a some examples to show how to use X-Reasoner with 🤗 Transformers or vLLM.
python
import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom qwen_vl_utils import process_vision_info # default: Load the model on the available device(s)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "microsoft/X-Reasoner-7B", dtype=torch.bfloat16, device_map="auto") # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(# "microsoft/X-Reasoner",# dtype=torch.bfloat16,# attn_implementation="flash_attention_2",# device_map="auto",# ) # You can set min_pixels and max_pixels according to your needs.min_pixels = 262144max_pixels = 262144processor = AutoProcessor.from_pretrained("microsoft/X-Reasoner-7B", min_pixels=min_pixels, max_pixels=max_pixels) # Multiple Choice Querymessages = [ { "role": "user", "content": [ {"type": "text", "text": "You should provide your thoughts within <think> </think> tags, then answer with just one of the options below within <answer> </answer> tags (For example, if the question is \n'Is the earth flat?\n A: Yes \nB: No', you should answer with <think>...</think> <answer>B: No</answer>). \nHere is the question:"}, { "type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", }, {"type": "text", "text": "Is there a dog in the image? A. Yes B. No"}, ], }] # Preparation for inferencetext = 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",) inputs = inputs.to(device="cuda") # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=4000)generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)print(output_text)Here we show an example of how to use X-Reasoner-7B with vLLM (tested with vLLM==0.11.2 and transformers==4.57.1):
python
from vllm import LLM, SamplingParamsfrom transformers import AutoProcessor min_pixels = 262144max_pixels = 262144processor = AutoProcessor.from_pretrained("microsoft/X-Reasoner-7B", min_pixels=min_pixels, max_pixels=max_pixels) llm = LLM( model="microsoft/X-Reasoner-7B", trust_remote_code=True, dtype="bfloat16", max_model_len=8192, tensor_parallel_size=4, gpu_memory_utilization=0.8, limit_mm_per_prompt={"image": 1}) # Set up sampling parameterssampling_params = SamplingParams( temperature=0.6, max_tokens=4000,) image_data = [] # Multiple Choice Queryimage_data = ['https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg']messages = [ { "role": "user", "content": [ { "type": "image", "image": image_data[0], }, {"type": "text", "text": "You should provide your thoughts within <think> </think> tags, then answer with just one of the options below within <answer> </answer> tags (For example, if the question is \n'Is the earth flat?\n A: Yes \nB: No', you should answer with <think>...</think> <answer>B: No</answer>). \nHere is the question: Is there a dog in the picture? A: Yes B: No"}, ], }] prompt = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True) if image_data: mm_prompt = { "prompt": prompt, "multi_modal_data": {"image": image_data} }else: mm_prompt = {"prompt": prompt} # Generate responseoutputs = llm.generate([mm_prompt], sampling_params) # Print the generated responsefor output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt}") print(f"Generated text: {generated_text}") print("-" * 50)</think> as a stop token to the assistant output and re-run to generate the final answer.If you find our work helpful, feel free to give us a cite.
text
@misc{liu2025xreasonergeneralizablereasoningmodalities, title={X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains}, author={Qianchu Liu and Sheng Zhang and Guanghui Qin and Timothy Ossowski and Yu Gu and Ying Jin and Sid Kiblawi and Sam Preston and Mu Wei and Paul Vozila and Tristan Naumann and Hoifung Poon}, year={2025}, eprint={2505.03981}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2505.03981}, }import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom qwen_vl_utils import process_vision_info # default: Load the model on the available device(s)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "microsoft/X-Reasoner-7B", dtype=torch.bfloat16, device_map="auto") # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(# "microsoft/X-Reasoner",# dtype=torch.bfloat16,# attn_implementation="flash_attention_2",# device_map="auto",# ) # You can set min_pixels and max_pixels according to your needs.min_pixels = 262144max_pixels = 262144processor = AutoProcessor.from_pretrained("microsoft/X-Reasoner-7B", min_pixels=min_pixels, max_pixels=max_pixels) # Multiple Choice Querymessages = [ { "role": "user", "content": [ {"type": "text", "text": "You should provide your thoughts within <think> </think> tags, then answer with just one of the options below within <answer> </answer> tags (For example, if the question is \n'Is the earth flat?\n A: Yes \nB: No', you should answer with <think>...</think> <answer>B: No</answer>). \nHere is the question:"}, { "type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", }, {"type": "text", "text": "Is there a dog in the image? A. Yes B. No"}, ], }] # Preparation for inferencetext = 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",) inputs = inputs.to(device="cuda") # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=4000)generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)print(output_text)from vllm import LLM, SamplingParamsfrom transformers import AutoProcessor min_pixels = 262144max_pixels = 262144processor = AutoProcessor.from_pretrained("microsoft/X-Reasoner-7B", min_pixels=min_pixels, max_pixels=max_pixels) llm = LLM( model="microsoft/X-Reasoner-7B", trust_remote_code=True, dtype="bfloat16", max_model_len=8192, tensor_parallel_size=4, gpu_memory_utilization=0.8, limit_mm_per_prompt={"image": 1}) # Set up sampling parameterssampling_params = SamplingParams( temperature=0.6, max_tokens=4000,) image_data = [] # Multiple Choice Queryimage_data = ['https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg']messages = [ { "role": "user", "content": [ { "type": "image", "image": image_data[0], }, {"type": "text", "text": "You should provide your thoughts within <think> </think> tags, then answer with just one of the options below within <answer> </answer> tags (For example, if the question is \n'Is the earth flat?\n A: Yes \nB: No', you should answer with <think>...</think> <answer>B: No</answer>). \nHere is the question: Is there a dog in the picture? A: Yes B: No"}, ], }] prompt = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True) if image_data: mm_prompt = { "prompt": prompt, "multi_modal_data": {"image": image_data} }else: mm_prompt = {"prompt": prompt} # Generate responseoutputs = llm.generate([mm_prompt], sampling_params) # Print the generated responsefor output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt}") print(f"Generated text: {generated_text}") print("-" * 50)@misc{liu2025xreasonergeneralizablereasoningmodalities, title={X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains}, author={Qianchu Liu and Sheng Zhang and Guanghui Qin and Timothy Ossowski and Yu Gu and Ying Jin and Sid Kiblawi and Sam Preston and Mu Wei and Paul Vozila and Tristan Naumann and Hoifung Poon}, year={2025}, eprint={2505.03981}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2505.03981}, }