DrMedra4b-179916

This is a merged LoRA model based on Google's MedGemma-4b-it, fine-tuned for medical applications.

Model Details

• Base Model: google/medgemma-4b-it
• Checkpoint: 179916
• Format: SafeTensors
• Architecture: Gemma3
• Fine-tuning Method: LoRA (Low-Rank Adaptation)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
model_name = "DrMedra4b-179916"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Example usage
prompt = "What are the symptoms of diabetes?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Configuration

• LoRA Rank: 198
• LoRA Alpha: 64
• Learning Rate: 2.5e-6
• Batch Size: 4
• Sequence Length: 768
• Epochs: 2.0

License

This model inherits the license from the base model (google/medgemma-4b-it).