GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wannaphong
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
wannaphong
Model Tree
Qwen/Qwen3-VL-2B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
prompt = """Extract all text from the image. Instructions:- Only return the clean Markdown.- Do not include any explanation or extra text.- You must include all information on the page. Formatting Rules:- Tables: Render tables using <table>...</table> in clean HTML format.- Equations: Render equations using LaTeX syntax with inline ($...$) and block ($$...$$).- Images/Charts/Diagrams: Wrap any clearly defined visual areas (e.g. charts, diagrams, pictures) in: <figure>Describe the image's main elements (people, objects, text), note any contextual clues (place, event, culture), mention visible text and its meaning, provide deeper analysis when relevant (especially for financial charts, graphs, or documents), comment on style or architecture if relevant, then give a concise overall summary. Describe in Thai.</figure> - Page Numbers: Wrap page numbers in <page_number>...</page_number> (e.g., <page_number>14</page_number>).- Checkboxes: Use ☐ for unchecked and ☑ for checked boxes."""Full inference code available on Colab Using Typhoon-OCR Package
bash
pip install typhoon-ocr -Upython
from typhoon_ocr import ocr_document # please set env TYPHOON_OCR_API_KEY or OPENAI_API_KEY to use this functionmarkdown = ocr_document("test.png", model = "typhoon-ocr", figure_language = "Thai", task_type = "v1.5")print(markdown)Local Model via vllm (GPU Required):
bash
pip install vllmvllm serve scb10x/typhoon-ocr1.5-2b --max-model-len 49152 --served-model-name typhoon-ocr-1-5 # OpenAI Compatible at http://localhost:8000 (or other port)# then you can supply base_url in to ocr_documentpython
from typhoon_ocr import ocr_documentmarkdown = ocr_document('image.png', model = "typhoon-ocr" , figure_language = "Thai" , task_type="v1.5", base_url='http://localhost:8000/v1', api_key='no-key')print(markdown)To read more about vllm
Local Model - Transformers (GPU Required):
python
from transformers import AutoModelForImageTextToText, AutoProcessorfrom PIL import Image def resize_if_needed(img, max_size): width, height = img.size # Only resize if one dimension exceeds max_size if width > 300 or height > 300: if width >= height: scale = max_size / float(width) new_size = (max_size, int(height * scale)) else: scale = max_size / float(height) new_size = (int(width * scale), max_size) img = img.resize(new_size, Image.Resampling.LANCZOS) print(f"{width, height}==> {img.size}") return img else: return img model = AutoModelForImageTextToText.from_pretrained( "scb10x/typhoon-ocr1.5-2b", dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained("scb10x/typhoon-ocr1.5-2b") img = Image.open("image.png") #This is important because the model is trained with a fixed image dimension of 1800 pximg = resize_if_needed(img, 1800) messages = [ { "role": "user", "content": [ { "type": "image", "image": img, }, { "type": "text", "text": prompt } ], } ] # Preparation for inferenceinputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt")inputs = inputs.to(model.device) # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=10000)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[0])We recommend to inference typhoon-ocr using vllm instead of huggingface transformers, and using typhoon-ocr library to ocr documents. To read more about vllm
bash
pip install vllmvllm serve scb10x/typhoon-ocr1.5-2b --max-model-len 49152 --served-model-name typhoon-ocr-1-5 # OpenAI Compatible at http://localhost:8000# then you can supply base_url in to ocr_documentpython
from typhoon_ocr import ocr_documentmarkdown = ocr_document('image.png', model = "typhoon-ocr" , figure_language = "Thai", task_type="v1.5", base_url='http://localhost:8000/v1', api_key='no-key')print(markdown)We recommend running Typhoon-OCR on-device using Ollama.
This is a task-specific model intended to be used only with the provided prompts. It does not include any guardrails or VQA capability. Due to the nature of large language models (LLMs), a certain level of hallucination may occur. We recommend that developers carefully assess these risks in the context of their specific use case.
https://twitter.com/opentyphoon
text
@misc{nonesung2026typhoonocropenvisionlanguage, title={Typhoon OCR: Open Vision-Language Model For Thai Document Extraction}, author={Surapon Nonesung and Natapong Nitarach and Teetouch Jaknamon and Pittawat Taveekitworachai and Kunat Pipatanakul}, year={2026}, eprint={2601.14722}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2601.14722}, }prompt = """Extract all text from the image. Instructions:- Only return the clean Markdown.- Do not include any explanation or extra text.- You must include all information on the page. Formatting Rules:- Tables: Render tables using <table>...</table> in clean HTML format.- Equations: Render equations using LaTeX syntax with inline ($...$) and block ($$...$$).- Images/Charts/Diagrams: Wrap any clearly defined visual areas (e.g. charts, diagrams, pictures) in: <figure>Describe the image's main elements (people, objects, text), note any contextual clues (place, event, culture), mention visible text and its meaning, provide deeper analysis when relevant (especially for financial charts, graphs, or documents), comment on style or architecture if relevant, then give a concise overall summary. Describe in Thai.</figure> - Page Numbers: Wrap page numbers in <page_number>...</page_number> (e.g., <page_number>14</page_number>).- Checkboxes: Use ☐ for unchecked and ☑ for checked boxes."""from typhoon_ocr import ocr_document # please set env TYPHOON_OCR_API_KEY or OPENAI_API_KEY to use this functionmarkdown = ocr_document("test.png", model = "typhoon-ocr", figure_language = "Thai", task_type = "v1.5")print(markdown)pip install vllmvllm serve scb10x/typhoon-ocr1.5-2b --max-model-len 49152 --served-model-name typhoon-ocr-1-5 # OpenAI Compatible at http://localhost:8000 (or other port)# then you can supply base_url in to ocr_documentfrom typhoon_ocr import ocr_documentmarkdown = ocr_document('image.png', model = "typhoon-ocr" , figure_language = "Thai" , task_type="v1.5", base_url='http://localhost:8000/v1', api_key='no-key')print(markdown)from transformers import AutoModelForImageTextToText, AutoProcessorfrom PIL import Image def resize_if_needed(img, max_size): width, height = img.size # Only resize if one dimension exceeds max_size if width > 300 or height > 300: if width >= height: scale = max_size / float(width) new_size = (max_size, int(height * scale)) else: scale = max_size / float(height) new_size = (int(width * scale), max_size) img = img.resize(new_size, Image.Resampling.LANCZOS) print(f"{width, height}==> {img.size}") return img else: return img model = AutoModelForImageTextToText.from_pretrained( "scb10x/typhoon-ocr1.5-2b", dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained("scb10x/typhoon-ocr1.5-2b") img = Image.open("image.png") #This is important because the model is trained with a fixed image dimension of 1800 pximg = resize_if_needed(img, 1800) messages = [ { "role": "user", "content": [ { "type": "image", "image": img, }, { "type": "text", "text": prompt } ], } ] # Preparation for inferenceinputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt")inputs = inputs.to(model.device) # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=10000)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[0])pip install vllmvllm serve scb10x/typhoon-ocr1.5-2b --max-model-len 49152 --served-model-name typhoon-ocr-1-5 # OpenAI Compatible at http://localhost:8000# then you can supply base_url in to ocr_documentfrom typhoon_ocr import ocr_documentmarkdown = ocr_document('image.png', model = "typhoon-ocr" , figure_language = "Thai", task_type="v1.5", base_url='http://localhost:8000/v1', api_key='no-key')print(markdown)@misc{nonesung2026typhoonocropenvisionlanguage, title={Typhoon OCR: Open Vision-Language Model For Thai Document Extraction}, author={Surapon Nonesung and Natapong Nitarach and Teetouch Jaknamon and Pittawat Taveekitworachai and Kunat Pipatanakul}, year={2026}, eprint={2601.14722}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2601.14722}, }