kuotient/Meta-Llama-3-8B-Instruct
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 Grouped-Query Attention (GQA) and is fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). This model excels in assistant-like chat applications and demonstrates strong performance across various benchmarks, including MMLU and HumanEval.
Loading preview...
Model Overview
kuotient/Meta-Llama-3-8B-Instruct is an 8 billion parameter instruction-tuned model from Meta's Llama 3 family, designed for generative text and code. It features an optimized transformer architecture with Grouped-Query Attention (GQA) for improved inference scalability and is fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. The model was trained on over 15 trillion tokens of publicly available online data, with a knowledge cutoff of March 2023.
Key Capabilities
- Dialogue Optimization: Specifically instruction-tuned for assistant-like chat and dialogue use cases.
- Enhanced Performance: Outperforms many open-source chat models on common industry benchmarks, showing significant improvements over Llama 2 models in areas like MMLU (68.4), HumanEval (62.2), and GSM-8K (79.6).
- Safety & Responsibility: Developed with a strong focus on helpfulness and safety, incorporating extensive red teaming, adversarial evaluations, and safety mitigations. It is designed to be less prone to false refusals compared to Llama 2.
- Commercial & Research Use: Intended for commercial and research applications primarily in English, with potential for fine-tuning in other languages under license.
Good For
- Assistant-like Chatbots: Its instruction-tuned nature makes it ideal for building conversational AI agents.
- General Text Generation: Adaptable for various natural language generation tasks.
- Code Generation: Demonstrates strong performance in coding benchmarks like HumanEval.
- English-centric Applications: Optimized for use in English-language contexts, though fine-tuning for other languages is possible.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.