GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
devanshty
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
devanshty
Model Tree
Qwen/Qwen2-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Babel is a Qwen2-VL LoRA adapter fine-tuned for multilingual OCR (Optical Character Recognition) and translation tasks. It can extract text from images across multiple languages and translate between them, making it ideal for document digitization, cross-language content processing, and international business automation.
Qwen/Qwen2-VL-7B-Instruct| File | Description |
|---|---|
adapter_model.safetensors | LoRA adapter weights |
adapter_config.json | PEFT adapter configuration |
tokenizer.json | Tokenizer vocabulary |
tokenizer_config.json | Tokenizer configuration |
python
from transformers import AutoProcessor, Qwen2VLForConditionalGenerationfrom peft import PeftModelfrom PIL import Imagefrom huggingface_hub import snapshot_download # Download adapteradapter_dir = snapshot_download(repo_id='devanshty/Babel') # Load base modelbase_model = Qwen2VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(adapter_dir) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, adapter_dir)model.eval() # OCR + Translateimage = Image.open("document.jpg")messages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "Extract all text from this image and translate it to English."} ] }]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)output = model.generate(**inputs, max_new_tokens=1024)print(processor.decode(output[0], skip_special_tokens=True))python
from huggingface_hub import hf_hub_downloadadapter = hf_hub_download(repo_id='devanshty/Babel', filename='adapter_model.safetensors')from transformers import AutoProcessor, Qwen2VLForConditionalGenerationfrom peft import PeftModelfrom PIL import Imagefrom huggingface_hub import snapshot_download # Download adapteradapter_dir = snapshot_download(repo_id='devanshty/Babel') # Load base modelbase_model = Qwen2VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(adapter_dir) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, adapter_dir)model.eval() # OCR + Translateimage = Image.open("document.jpg")messages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "Extract all text from this image and translate it to English."} ] }]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)output = model.generate(**inputs, max_new_tokens=1024)print(processor.decode(output[0], skip_special_tokens=True))from huggingface_hub import hf_hub_downloadadapter = hf_hub_download(repo_id='devanshty/Babel', filename='adapter_model.safetensors')