OpenBuddy/openbuddy-llama3-8b-v21.1-8k

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Apr 20, 2024License:llama3Architecture:Transformer0.0K Featherless Exclusive Warm

OpenBuddy/openbuddy-llama3-8b-v21.1-8k is an 8 billion parameter multilingual chatbot developed by OpenBuddy, built upon Meta Llama 3. This model is specifically fine-tuned for chat applications in both English and Chinese, offering an 8192-token context length. It is designed to be a helpful, respectful, and honest AI assistant, optimized for safe and unbiased responses.

Loading preview...

OpenBuddy/openbuddy-llama3-8b-v21.1-8k Overview

OpenBuddy/openbuddy-llama3-8b-v21.1-8k is an 8 billion parameter multilingual chatbot model developed by the OpenBuddy team, leveraging the Meta Llama 3 architecture. It is specifically designed for conversational AI, with a strong focus on both English and Chinese languages. The model features an 8192-token context window, enabling it to handle longer and more complex interactions.

Key Capabilities

  • Multilingual Chat: Optimized for fluent and contextually appropriate conversations in English and Chinese.
  • Instruction Following: Designed to act as a helpful, respectful, and honest AI assistant, adhering to safety guidelines.
  • Robust Prompt Format: Utilizes a specific prompt format (<|role|>system<|says|>...<|end|>) for structured conversations, compatible with transformers fast tokenizer and vllm for OpenAI-like API deployment.
  • Ethical AI: Trained to avoid harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content, ensuring socially unbiased and positive responses.

Good For

  • General-purpose Chatbots: Ideal for building conversational agents that require strong performance in both English and Chinese.
  • Multilingual Applications: Suitable for applications needing to interact with users across these two major languages.
  • Safe and Controlled Environments: Its emphasis on safety and unbiased responses makes it appropriate for public-facing AI assistants where content moderation is crucial.

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