tda45/TdAI

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 3, 2026License:gpl-3.0Architecture:Transformer Open Weights Featherless Exclusive Cold

TdAI is an 8 billion parameter instruction-tuned causal language model developed by tda45, based on the NousResearch/Hermes-3-Llama-3.1-8B architecture. This model is fine-tuned for chat, roleplaying, and function calling, leveraging synthetic data and distillation techniques. It supports a 32K context length and is designed for general conversational AI applications.

Loading preview...

TdAI Model Overview

TdAI is an 8 billion parameter instruction-tuned language model developed by tda45, built upon the NousResearch/Hermes-3-Llama-3.1-8B base model. It features a substantial 32,768 token context window, enabling it to handle longer and more complex conversational interactions.

Key Capabilities

  • Instruction Following: Fine-tuned to accurately follow instructions for various tasks.
  • Chat and Roleplaying: Optimized for engaging in dynamic conversations and adopting specific personas.
  • Function Calling: Designed to support function calling, allowing integration with external tools and APIs.
  • JSON Mode: Capable of generating structured JSON output, useful for programmatic interactions.
  • Synthetic Data Training: Utilizes synthetic data and distillation methods to enhance performance and robustness.

Good For

  • General Chatbots: Ideal for creating interactive and responsive conversational agents.
  • Roleplaying Scenarios: Excels in applications requiring the model to maintain a consistent character or role.
  • Automated Assistants: Suitable for tasks that involve understanding user intent and executing specific functions.
  • Structured Output Generation: Useful for developers needing reliable JSON output from an LLM.