asolomonqa/asmgenius-v1

⚙️ AsmGenius v1

A specialized assembly language AI fine-tuned on 7,167 x86-64 and ARM64 examples.

Base Model

CodeLlama-7B-Instruct fine-tuned with QLoRA

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model     = AutoModelForCausalLM.from_pretrained("asolomonqa/asmgenius-v1")
tokenizer = AutoTokenizer.from_pretrained("asolomonqa/asmgenius-v1")

Training

• Method: QLoRA (4-bit quantization + LoRA adapters)
• Dataset: 7,167 assembly code prompt/response pairs
• Architectures: x86-64 (NASM) and ARM64 (GNU AS)
• Platform: Google Colab T4 GPU