GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Abhiram1404
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
Abhiram1404
Model Tree
unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
Trained on real scanned documents from RVL-CDIP
(38.7 GB tarball, 16 document classes — letter, form, invoice, resume, memo, etc.) paired with real
per-image OCR annotations from jordyvl/rvl_cdip_easyocr
(EasyOCR word/box outputs, reconstructed into reading-order text lines).
Caveat: RVL-CDIP is built from 1990s tobacco-litigation document scans — real scan artifacts, but era-appropriate layouts (e.g. its "resume" class looks typewriter/dot-matrix-era, not like a modern resume). Ground truth is EasyOCR's own output, not human transcription, so it inherits EasyOCR's error rate on these low-quality scans.
FastVisionModel.get_peft_model, r=16, lora_alpha=16, lora_dropout=0,
target_modules="all-linear", adapters on both vision and language layers (attention + MLP).load_in_4bit=True) with "unsloth" gradient checkpointing.SFTTrainer with UnslothVisionDataCollator, batch size 1, gradient accumulation 8
(effective batch size 8), 120 steps, learning_rate=2e-4, linear schedule with 5 warmup steps,
adamw_8bit, bf16/fp16 mixed precision, max_seq_length=2048.python
from unsloth import FastVisionModelmodel, tokenizer = FastVisionModel.from_pretrained("Abhiram1404/qwen2vl-doc-ocr-lora",load_in_4bit=True,)FastVisionModel.for_inference(model)instruction = "Extract all the text from this document image, preserving line order."messages = [{"role": "user", "content": [{"type": "image", "image": image}, {"type": "text", "text": instruction}]}]input_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True)inputs = tokenizer(image, input_text, add_special_tokens=False, return_tensors="pt").to("cuda")output_ids = model.generate(**inputs, max_new_tokens=512, temperature=0.2, do_sample=True)print(tokenizer.decode(output_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))