# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("elenamagdy77/Finetune_Llama_3_2_Vision_OCR", device_map="auto")Quick Links
Fine-tuned LLaMA 3.2 Vision for Medical OCR
🎯 Model Info
- Base: unsloth/Llama-3.2-11B-Vision-Instruct
- Training Loss: 0.9361
- Steps: 30
- Method: LoRA fine-tuning
🚀 Usage
from unsloth import FastVisionModel
model, tokenizer = FastVisionModel.from_pretrained(
"elenamagdy77/Finetune_Llama_3_2_Vision_OCR",
load_in_4bit=True,
use_gradient_checkpointing="unsloth",
)
FastVisionModel.for_inference(model)
📊 Performance
Optimized for medical prescription OCR tasks.
Model tree for elenamagdy77/Finetune_Llama_3_2_Vision_OCR
Base model
meta-llama/Llama-3.2-11B-Vision-Instruct Finetuned
unsloth/Llama-3.2-11B-Vision-Instruct
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="elenamagdy77/Finetune_Llama_3_2_Vision_OCR")