neverland-th/neverland-custom-ai

TEXT GENERATIONPricing:Input $0.2036 / Output $1.34Concurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 27, 2024License:llama3.1Architecture:Transformer Featherless Exclusive Cold

The neverland-th/neverland-custom-ai is a 3.2 billion parameter instruction-tuned causal language model developed by neverland-th, based on Meta's Llama-3.2-3B-Instruct architecture. It features a substantial 32768-token context window, making it suitable for processing longer conversations and documents. This model is specifically fine-tuned for conversational AI and chatbot applications, leveraging datasets like HuggingFaceTB/everyday-conversations-llama3.1-2k and nvl-og/chat to enhance its dialogue capabilities in both English and Thai.

Loading preview...

neverland-th/neverland-custom-ai: A Conversational AI Model

The neverland-th/neverland-custom-ai is a 3.2 billion parameter instruction-tuned language model, built upon Meta's Llama-3.2-3B-Instruct architecture. It is designed for conversational AI and chatbot applications, offering a large context window of 32768 tokens to handle extensive dialogues and complex prompts. This model is particularly notable for its multilingual capabilities, supporting both English and Thai.

Key Capabilities

  • Advanced Conversational AI: Fine-tuned on diverse dialogue datasets, including HuggingFaceTB/everyday-conversations-llama3.1-2k and nvl-og/chat, to enhance natural and coherent conversation flow.
  • Extended Context Understanding: With a 32768-token context length, it can process and maintain context over long interactions, making it suitable for detailed discussions or document analysis.
  • Multilingual Support: Optimized for use in both English and Thai language environments, catering to a broader user base.
  • Instruction Following: As an instruction-tuned model, it is adept at understanding and executing specific user commands and queries.

Good For

  • Developing chatbots and virtual assistants requiring deep conversational understanding.
  • Applications needing to process and generate long-form text or maintain context over extended dialogues.
  • Building AI solutions for English and Thai-speaking users.
  • Tasks involving complex instruction following and multi-turn conversations.

Finetunes
2 models