18-Death/sq-atbash-base64-gsm8k

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 16, 2026Architecture:Transformer Cold

The 18-Death/sq-atbash-base64-gsm8k model is a 3.1 billion parameter language model fine-tuned using the TRL framework. It is designed for general text generation tasks, as demonstrated by its ability to respond to open-ended questions. With a context length of 32768 tokens, it can process substantial input for various conversational and creative applications.

Loading preview...

Model Overview

The 18-Death/sq-atbash-base64-gsm8k is a 3.1 billion parameter language model that has been fine-tuned using the TRL library. This model is built for general text generation, capable of producing coherent and contextually relevant responses to a wide array of prompts.

Key Capabilities

  • General Text Generation: Excels at generating human-like text based on given prompts, suitable for creative writing, conversational AI, and content creation.
  • Long Context Handling: Features a substantial context length of 32768 tokens, allowing it to maintain coherence and draw information from extensive inputs.
  • Fine-tuned Performance: Benefits from Supervised Fine-Tuning (SFT) using TRL, enhancing its ability to follow instructions and generate relevant outputs.

Training Details

The model was trained with SFT using the following framework versions:

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

Use Cases

This model is well-suited for applications requiring:

  • Interactive Chatbots: Generating responses in conversational agents.
  • Creative Content Generation: Assisting with writing stories, scripts, or other creative texts.
  • Question Answering: Providing detailed answers to open-ended questions.