18-Death/mt-atbash-base64-aqua_rat

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 18, 2026Architecture:Transformer Featherless Exclusive Cold

mt-atbash-base64-aqua_rat is a 3.1 billion parameter language model developed by 18-Death, fine-tuned using the TRL framework. This model is designed for general text generation tasks, offering a 32,768 token context length. Its primary application is generating conversational responses and creative text based on user prompts.

Loading preview...

Model Overview

mt-atbash-base64-aqua_rat is a 3.1 billion parameter language model developed by 18-Death. It has been fine-tuned using the TRL (Transformers Reinforcement Learning) library, indicating a focus on improving its conversational and generative capabilities through advanced training techniques. The model supports a substantial context length of 32,768 tokens, allowing it to process and generate longer, more coherent text sequences.

Key Capabilities

  • General Text Generation: Capable of generating diverse text based on user prompts.
  • Conversational AI: Suitable for tasks requiring natural language responses, as demonstrated by its quick start example.
  • Extended Context: Benefits from a 32,768 token context window, enabling it to maintain coherence over longer interactions or documents.

Training Details

This model was trained using Supervised Fine-Tuning (SFT) within the TRL framework. The training utilized specific versions of key libraries:

  • TRL: 1.3.0
  • Transformers: 5.6.2
  • Pytorch: 2.10.0
  • Datasets: 4.8.4
  • Tokenizers: 0.22.2

Good For

  • Developing chatbots and conversational agents.
  • Generating creative content, stories, or dialogue.
  • Applications requiring understanding and generation of long-form text.