Qwen3.5-0.8B-vision-LORA-16bit

pip install unsloth transformers peft trl torch pillow

from unsloth import FastVisionModel
from PIL import Image

model, tokenizer = FastVisionModel.from_pretrained(
    model_name="Mustafaege/Qwen3.5-0.8B-vision-LORA-16bit",
)
FastVisionModel.for_inference(model)

image = Image.open("formula.png")

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Write the LaTeX representation for this image."},
        ],
    }
]

input_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
inputs = tokenizer(image, input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
# Example: \frac{d}{dx}\left(e^{x}\right) = e^{x}

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "unsloth/Qwen3.5-0.8B"
adapter_id    = "Mustafaege/Qwen3.5-0.8B-vision-LORA-16bit"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype="auto",
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

from unsloth import FastVisionModel

model, tokenizer = FastVisionModel.from_pretrained(
    model_name="Mustafaege/Qwen3.5-0.8B-vision-LORA-16bit",
)

# Merge LoRA into base weights
model.save_pretrained_merged("Qwen3.5-0.8B-vision-OCR-merged", tokenizer)

@misc{mustafaege2026qwen35visionocr,
  title   = {Qwen3.5-0.8B Vision OCR: 16-bit LoRA Adapter for Image-to-LaTeX},
  author  = {Mustafaege},
  year    = {2026},
  url     = {https://huggingface.co/Mustafaege/Qwen3.5-0.8B-vision-LORA-16bit}
}

@misc{qwen3_5,
  title     = {Qwen3.5 Technical Report},
  author    = {Qwen Team},
  year      = {2025},
  publisher = {Alibaba Cloud}
}