RedHatAI/TinyLlama-1.1B-Chat-v1.0

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.1BQuant:BF16Context Size:2kPublished:Jun 4, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

RedHatAI/TinyLlama-1.1B-Chat-v1.0 is a 1.1 billion parameter Llama-based conversational model, developed by the TinyLlama project. It is fine-tuned for chat applications, leveraging the Zephyr training recipe and aligned using DPO on the UltraFeedback dataset. This compact model is designed for applications requiring restricted computation and memory footprints, making it suitable for efficient, on-device conversational AI.

Loading preview...

TinyLlama-1.1B-Chat-v1.0 Overview

RedHatAI/TinyLlama-1.1B-Chat-v1.0 is a compact, 1.1 billion parameter language model built on the Llama architecture. Developed by the TinyLlama project, its primary goal was to pretrain a Llama model on 3 trillion tokens, making it highly compatible with existing Llama-based open-source projects due to its identical architecture and tokenizer.

Key Capabilities

  • Conversational AI: This model is specifically fine-tuned for chat applications, following the Hugging Face Zephyr training recipe.
  • Instruction Following: Initially fine-tuned on a variant of the UltraChat dataset, which contains diverse synthetic dialogues generated by ChatGPT.
  • Preference Alignment: Further aligned using 🤗 TRL's DPOTrainer on the openbmb/UltraFeedback dataset, which includes 64k prompts and GPT-4 ranked model completions.
  • Compact Design: With only 1.1 billion parameters, it is optimized for scenarios demanding restricted computation and memory resources.

Good For

  • Edge Devices: Its small size makes it suitable for deployment on devices with limited computational power.
  • Efficient Chatbots: Ideal for building responsive and resource-efficient conversational agents.
  • Llama Ecosystem Integration: Seamlessly integrates into projects already utilizing the Llama architecture and tokenizer.

Finetunes
3 models