This model is a fine-tuned variant of Gemma-2-2b, optimized for medical transcription tasks with efficient 4-bit quantization and Low-Rank Adaptation (LoRA). It handles transcription processing, keyword extraction, and medical specialty classification.

Model Details

Developed by: Harish Nair
Organization: University of Ottawa
License: Apache 2.0
Fine-tuned from: Gemma-2-2b
Model type: Transformer-based language model for medical transcription processing
Language(s): English

Training Details

Training Configuration:
- LoRA with r=8, targeting specific transformer modules for adaptation.
- 4-bit quantization using nf4 quantization type and bfloat16 compute precision.

How to Use

To load and use this model, initialize it with the following configuration:

python

import pandas as pd
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import LoraConfig, PeftModel

model_id = "harishnair04/Gemma-medtr-2b-sft-v2"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id, token=access_token_read)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map='auto', token=access_token_read)