DavidLanz/Llama3-tw-8B-Instruct

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 1, 2024License:llama3Architecture:Transformer0.0K Featherless Exclusive Cold

DavidLanz/Llama3-tw-8B-Instruct is an 8 billion parameter instruction-tuned large language 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 a context length of 8192 tokens. This model is designed for assistant-like chat and general natural language generation tasks, outperforming many open-source chat models on common industry benchmarks.

Loading preview...

Model Overview

DavidLanz/Llama3-tw-8B-Instruct is an 8 billion parameter instruction-tuned model from Meta's Llama 3 family, designed for dialogue and general natural language generation. It is built on an optimized transformer architecture, incorporating Grouped-Query Attention (GQA) for enhanced inference scalability, and supports an 8192-token context length. The model was trained on over 15 trillion tokens of publicly available data, with fine-tuning including publicly available instruction datasets and over 10 million human-annotated examples. The training data cutoff for this 8B model is March 2023.

Key Capabilities

  • Optimized for Dialogue: Specifically instruction-tuned for assistant-like chat applications.
  • Strong Benchmark Performance: Outperforms many other open-source chat models on standard industry benchmarks, showing significant improvements over Llama 2 models across various general, knowledge reasoning, and reading comprehension tasks.
  • Enhanced Safety & Helpfulness: Developed with a focus on optimizing helpfulness and safety, demonstrating reduced false refusal rates compared to Llama 2.
  • Code Generation: Capable of generating code, as indicated by its performance on benchmarks like HumanEval (62.2% for the instruction-tuned 8B model).

Good For

  • Assistant-like Chatbots: Ideal for building conversational AI agents.
  • Natural Language Generation: Suitable for a wide range of text generation tasks in English.
  • Commercial and Research Use: Intended for both commercial applications and academic research.
  • Fine-tuning: Developers can fine-tune the model for specific use cases or languages beyond English, adhering to the Llama 3 Community License.

Finetunes
2 models