GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
korea-deep-learning
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
korea-deep-learning
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct specialized for table recognition tasks. The model was trained using LoRA (Low-Rank Adaptation) and then merged with the base model for efficient inference.
Key Features:
merge_and_unload()python
import torchfrom transformers import AutoModelForVision2Seq, AutoProcessorfrom PIL import Image # Load model and processormodel = AutoModelForVision2Seq.from_pretrained( "korea-deep-learning/Qwen2.5-VL-7B-TableRecog", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True) processor = AutoProcessor.from_pretrained( "korea-deep-learning/Qwen2.5-VL-7B-TableRecog", trust_remote_code=True) # Prepare image and textimage = Image.open("table_image.png")text = "Extract the table content and structure from this image." # Process inputsinputs = processor(text=text, images=image, return_tensors="pt").to(model.device) # Generate outputwith torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=1024) result = processor.decode(outputs[0], skip_special_tokens=True)print(result)The model has been evaluated on table recognition tasks with the following metrics:
bibtex
@misc{qwen2.5-vl-tablerecog, author = {Korea Deep Learning Team}, title = {Qwen2.5-VL-7B-TableRecog: Table Recognition Model}, year = {2025}, publisher = {HuggingFace}, howpublished = {\url{https://huggingface.co/korea-deep-learning/Qwen2.5-VL-7B-TableRecog}},}This model inherits the Apache 2.0 license from the base Qwen2.5-VL-7B-Instruct model.
import torchfrom transformers import AutoModelForVision2Seq, AutoProcessorfrom PIL import Image # Load model and processormodel = AutoModelForVision2Seq.from_pretrained( "korea-deep-learning/Qwen2.5-VL-7B-TableRecog", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True) processor = AutoProcessor.from_pretrained( "korea-deep-learning/Qwen2.5-VL-7B-TableRecog", trust_remote_code=True) # Prepare image and textimage = Image.open("table_image.png")text = "Extract the table content and structure from this image." # Process inputsinputs = processor(text=text, images=image, return_tensors="pt").to(model.device) # Generate outputwith torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=1024) result = processor.decode(outputs[0], skip_special_tokens=True)print(result)@misc{qwen2.5-vl-tablerecog, author = {Korea Deep Learning Team}, title = {Qwen2.5-VL-7B-TableRecog: Table Recognition Model}, year = {2025}, publisher = {HuggingFace}, howpublished = {\url{https://huggingface.co/korea-deep-learning/Qwen2.5-VL-7B-TableRecog}},}