Llama-3.2-90B-Vision-Instruct: An Open-Source Multimodal Large Model - Free Deployment with Support for Visual Instruction Understanding

Llama 3.2 90B Vision Instruct Unsloth Bnb 4bit

Developed by unsloth

Meta Llama 3.2 series 90B-parameter multimodal large language model supporting visual instruction understanding, optimized with Unsloth dynamic 4-bit quantization

Text-to-Image

Transformers

English#Multimodal Visual Understanding #Efficient Fine-Tuning Optimization #Multilingual Dialogue Agent

Downloads 58

Release Time : 12/4/2024

Model Overview

A multimodal large language model based on the Meta Llama 3.2 architecture, supporting visual and text inputs, optimized for multilingual dialogue scenarios, suitable for tasks like agent retrieval and summarization. The Unsloth version significantly improves inference efficiency through dynamic 4-bit quantization technology.

Model Features

Dynamic 4-Bit Quantization

Uses Unsloth's patented technology to selectively avoid quantizing critical parameters, significantly improving model accuracy while maintaining low GPU memory usage.

Multimodal Support

Processes both visual and text inputs for cross-modal understanding and generation.

Efficient Fine-Tuning

Unsloth optimization achieves 5x faster training speed and 70% memory savings, supporting fine-tuning on consumer-grade GPUs.

Multilingual Optimization

Specifically optimized for dialogue capabilities in 8 core languages, with support for broader language expansion.

Model Capabilities

Visual question answering

Multilingual text generation

Image caption generation

Cross-modal retrieval

Multi-turn dialogue

Text summarization

Use Cases

Intelligent Assistant

Multimodal Customer Service Bot

Understands user queries through images and text to provide accurate responses

Supports complex queries involving product images and text descriptions simultaneously

Content Generation

Visual-Text Content Creation

Generates marketing copy or social media content based on visual input

Delivers high-quality outputs with consistent brand tone

Education

Interactive Learning Assistant

Analyzes textbook diagrams and generates explanatory content

Enhances learning efficiency in STEM subjects

🚀 unsloth/Llama-3.2-90B-Vision-Instruct-unsloth-bnb-4bit

Unsloth enables 5x faster finetuning of Llama 3.2, Gemma 2, and Mistral 2 with 70% less memory!

🚀 Quick Start

We have a free Google Colab Tesla T4 notebook for Llama 3.2 Vision (11B) here: Google Colab Notebook

✨ Features

Unsloth's Dynamic 4-bit Quants selectively avoids quantizing certain parameters, greatly improving accuracy while keeping VRAM usage similar to BnB 4-bit. See our full collection of Unsloth quants on Hugging Face here.

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Llama-3.2 (3B)	▶️ Start on Colab	2.4x faster	58% less
Llama-3.2 (11B vision)	▶️ Start on Colab	2x faster	60% less
Qwen2 VL (7B)	▶️ Start on Colab	1.8x faster	60% less
Qwen2.5 (7B)	▶️ Start on Colab	2x faster	60% less
Llama-3.1 (8B)	▶️ Start on Colab	2.4x faster	58% less
Phi-3.5 (mini)	▶️ Start on Colab	2x faster	50% less
Gemma 2 (9B)	▶️ Start on Colab	2.4x faster	58% less
Mistral (7B)	▶️ Start on Colab	2.2x faster	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

📚 Documentation

Special Thanks

A huge thank you to the Meta and Llama team for creating and releasing these models.

Model Information

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.

Property	Details
Model developer	Meta
Model Architecture	Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Supported languages	English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
Llama 3.2 family of models	Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date	Sept 25, 2024
Status	This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
License	Use of Llama 3.2 is governed by the Llama 3.2 Community License (a custom, commercial license agreement).

Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3.1 in applications, please go here.

📄 License

The use of this model is under the Llama 3.2 Community License.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご