Llama 3.3-70B-Instruct-AWQ Open-Source Large Language Model - Free Deployment with Support for Multilingual Conversations

Llama 3.3 70b Instruct Awq

Developed by casperhansen

Llama 3.3 is a multilingual large language model developed by Meta, with 70 billion parameters, optimized for multilingual dialogue use cases, and demonstrates excellent performance in multiple benchmarks.

Large Language Model

Transformers

Supports Multiple Languages#70B parameter large model #128k ultra-long context #8-language multilingual dialogue

Downloads 47.12k

Release Time : 12/6/2024

Model Overview

A pre-trained and instruction-tuned 70B parameter generative model supporting multilingual text input/output, optimized for dialogue scenarios.

Model Features

Multilingual Support

Supports text generation and dialogue in 8 major languages

Long Context Handling

128k tokens context length, suitable for processing long documents

Efficient Inference

Uses Grouped Query Attention (GQA) technology to improve inference efficiency

Reinforcement Learning Tuning

Optimized dialogue safety and helpfulness through RLHF (Reinforcement Learning from Human Feedback)

Model Capabilities

Multilingual text generation

Instruction following

Code generation

Mathematical reasoning

Tool usage

Use Cases

Dialogue Systems

Multilingual Customer Service Bot

Supports intelligent customer service conversations in multiple languages

Performs exceptionally well in non-English languages such as Thai and Hindi

Code Assistance

Programming Assistant

Helps developers generate and optimize code

Achieves 88.4% pass@1 on HumanEval benchmark

Educational Assistance

Math Problem Solving

Solves complex math problems and demonstrates reasoning processes

Scores 77.0 on MATH benchmark

🚀 Llama 3.3 70B Instruct AWQ Model

This is the AWQ version of the Llama 3.3 70B Instruct model, offering enhanced performance and efficiency. More details can be found at: https://github.com/casper-hansen/AutoAWQ.

🚀 Quick Start

This is the AWQ version of the Llama 3.3 70B Instruct model. Find more info here: https://github.com/casper-hansen/AutoAWQ.

✨ Features

Multilingual Support: Supports English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
Optimized Architecture: Uses an optimized transformer architecture with Grouped-Query Attention (GQA) for improved inference scalability.
Instruction Tuned: Tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) for better alignment with human preferences.

📚 Documentation

Model Information

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Model developer: Meta

Model Architecture: Llama 3.3 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.

Property	Details
Training Data	A new mix of publicly available online data.
Params	70B
Input modalities	Multilingual Text
Output modalities	Multilingual Text and code
Context length	128k
GQA	Yes
Token count	15T+
Knowledge cutoff	December 2023

Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Llama 3.3 model. Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.

Model Release Date:

70B Instruct: December 6, 2024

Status: This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.

License A custom commercial license, the Llama 3.3 Community License Agreement, is available at: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE

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 3.3 in applications, please go here.

Benchmark

Category	Benchmark	# Shots	Metric	Llama 3.1 8B Instruct	Llama 3.1 70B Instruct	Llama-3.3 70B Instruct	Llama 3.1 405B Instruct
	MMLU (CoT)	0	macro_avg/acc	73.0	86.0	86.0	88.6
	MMLU Pro (CoT)	5	macro_avg/acc	48.3	66.4	68.9	73.3
Steerability	IFEval			80.4	87.5	92.1	88.6
Reasoning	GPQA Diamond (CoT)	0	acc	31.8	48.0	50.5	49.0
Code	HumanEval	0	pass@1	72.6	80.5	88.4	89.0
	MBPP EvalPlus (base)	0	pass@1	72.8	86.0	87.6	88.6
Math	MATH (CoT)	0	sympy_intersection_score	51.9	68.0	77.0	73.8
Tool Use	BFCL v2	0	overall_ast_summary/macro_avg/valid	65.4	77.5	77.3	81.1
Multilingual	MGSM	0	em	68.9	86.9	91.1	91.6

📄 License

A custom commercial license, the Llama 3.3 Community License Agreement, is available at: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/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