NousResearch/Meta-Llama-3-8B-Instruct

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 18, 2024License:llama3Architecture:Transformer0.1K Warm

NousResearch/Meta-Llama-3-8B-Instruct is an 8 billion parameter instruction-tuned generative text model developed by Meta, part of the Llama 3 family. Optimized for dialogue use cases, it utilizes an optimized transformer architecture with a context length of 8192 tokens. This model is fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety, outperforming many open-source chat models on common benchmarks.

Loading preview...

Model Overview

NousResearch/Meta-Llama-3-8B-Instruct is an 8 billion parameter instruction-tuned model from Meta's Llama 3 family, designed for commercial and research use in English. It is optimized for dialogue and assistant-like chat applications, built upon an optimized transformer architecture with a context length of 8192 tokens. The model was trained on over 15 trillion tokens of publicly available data, with fine-tuning data including over 10 million human-annotated examples, and features Grouped-Query Attention (GQA) for improved inference scalability.

Key Capabilities & Performance

  • Dialogue Optimization: Specifically instruction-tuned for chat and assistant-like interactions, outperforming previous Llama 2 models and many other open-source chat models on industry benchmarks.
  • Enhanced Safety & Helpfulness: Developed with a strong focus on optimizing helpfulness and safety through SFT and RLHF, and significantly reduces false refusals compared to Llama 2.
  • Strong Benchmark Results: Demonstrates notable improvements across various benchmarks, including MMLU (68.4), HumanEval (62.2), and GSM-8K (79.6), showcasing its capabilities in reasoning, code generation, and mathematical tasks.

Intended Use Cases

  • Assistant-like Chatbots: Ideal for building conversational AI agents and virtual assistants.
  • Natural Language Generation: Adaptable for a variety of text generation tasks in English.
  • Commercial and Research Applications: Suitable for both commercial deployments and academic research, with a custom commercial license available.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p