kingabzpro

- Developed by: kingabzpro - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

`medgemma-brain-cancer` is a fine-tuned version of google/medgemma-4b-it, trained specifically for brain tumor diagnosis and classification from MRI scans. This model leverages vision-language learning for enhanced medical imaging interpretation. Base Model: google/medgemma-4b-it Dataset: orvile/brain-cancer-mri-dataset Fine-tuning Approach: Supervised fine-tuning (SFT) using Transformers Reinforcement Learning (TRL) Task: Brain tumor classification from MRI images Pipeline Tag: `image-text-to-text` Accuracy Improvement: Base model accuracy: 33% Fine-tuned model accuracy: 89% Explore the training pipeline, evaluation results, and experiments in the notebook: This model is intended for research and educational purposes related to medical imaging, specifically brain tumor classification. It is not a certified diagnostic tool and should not be used in clinical decision-making without further validation.

Fine-tuning Llama 4 (Scout 17B 16E) in 4-bit Quantization for Medical Reasoning This project fine-tunes the `meta-llama/Llama-4-Scout-17B-16E-Instruct` model using a medical reasoning dataset (`FreedomIntelligence/medical-o1-reasoning-SFT`) with 4-bit quantization for memory-efficient training. Make sure your Hugging Face token is stored in an environment variable: The notebook will automatically log you in using this token. 1. Load the Model and Tokenizer The script downloads the Llama 4 Scout model and applies 4-bit quantization with `BitsAndBytesConfig` for efficient memory usage. 2. Prepare the Dataset - The notebook uses `FreedomIntelligence/medical-o1-reasoning-SFT` (first 500 samples). - It formats each example into an instruction-following prompt with step-by-step chain-of-thought reasoning. 3. Fine-tuning - Fine-tuning is set up with PEFT (LoRA / Adapter Tuning style) to modify a small subset of model parameters. - TRL (Transformer Reinforcement Learning) is used to fine-tune efficiently. 4. Push Fine-tuned Model - After training, the fine-tuned model and tokenizer are pushed back to your Hugging Face account. Here is the training notebook: Finetuningllama4.ipynb) - Base Model: `meta-llama/Llama-4-Scout-17B-16E-Instruct` - Quantization: 4-bit (NF4) - Training: PEFT + TRL - Dataset: 500 examples from medical reasoning dataset - GPU Required: Make sure you have access to 3X H200s. Get it from RunPod for an hours. Training took only 7 minutes. - Environment: The notebook expects an environment where NVIDIA CUDA drivers are available (`nvidia-smi` check is included). - Memory Efficiency: 4-bit loading greatly reduces memory footprint.

This project fine-tunes the `microsoft/Phi-4-reasoning-plus` model using a medical reasoning dataset (`TheFinAI/Fino1ReasoningPathFinQA`). Make sure your Hugging Face token is stored in an environment variable: The notebook will automatically log you in using this token. 1. Load the Model and Tokenizer The script downloads the full Phi-4-reasoning-plus model. 2. Prepare the Dataset - The notebook uses `TheFinAI/Fino1ReasoningPathFinQA` (first 1000 samples). - It formats each example into an instruction-following prompt with step-by-step chain-of-thought reasoning. 3. Fine-tuning - Fine-tuning is set up with PEFT (LoRA / Adapter Tuning style) to modify a small subset of model parameters. - TRL (Transformer Reinforcement Learning) is used to fine-tune efficiently. 4. Push Fine-tuned Model - After training, the fine-tuned model and tokenizer are pushed back to your Hugging Face account. >> Here is the training notebook: FinetuningPhi-4-Reasoning-Plus - Base Model: `microsoft/Phi-4-reasoning-plus` - Training: PEFT + TRL - Dataset: 1000 examples FinQA reasoning dataset - GPU Required: Make sure you have access to 1X A100s. Get it from RunPod for an hours. Training took only 7 minutes. - Environment: The notebook expects an environment where NVIDIA CUDA drivers are available (`nvidia-smi` check is included).