PVIS2027-JT-6597/Llama-3.2-11B-Vision-SciVisCap

Llama-3.2-11B-Vision-SciVisCap

Built with Llama

This repository contains a LoRA adapter for meta-llama/Llama-3.2-11B-Vision-Instruct, trained on SciVisCap for scientific visualization (SciVis) figure captioning.

Training Configuration

• —Epochs: 3 (final checkpoint)
• —LoRA rank: 8
• —LoRA alpha: 32
• —Batch size: 8
• —Learning rate: 1e-4 (cosine schedule, warmup ratio 0.1)
• —Max sequence length: 4,096 tokens- Trained via Unsloth

Base model access: meta-llama/Llama-3.2-11B-Vision-Instruct is gated -- request access on its model page with the account you'll use to load this adapter.

Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.