TanayJalan/omnimind-mistral-7b-mlqa

OmniMind — Mistral 7B Fine-tuned on AI/ML Q&A

Fine-tuned version of Mistral 7B Instruct for answering AI and Machine Learning questions.

Training Details

• Base model: mistralai/Mistral-7B-Instruct-v0.2
• Method: QLoRA (4-bit quantisation + LoRA adapters)
• Dataset: ~220 synthetic AI/ML Q&A pairs
• Hardware: Google Colab T4 GPU
• Epochs: 3

Example Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("TanayJalan/omnimind-mistral-7b-mlqa")

Topics Covered

Gradient descent, transformers, RAG, fine-tuning, LoRA, CNNs, LSTMs, MLOps, vector databases, and more.