18-Death/sq-bijection-atbash-ecqa

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

The 18-Death/sq-bijection-atbash-ecqa is a 3.1 billion parameter language model fine-tuned by 18-Death. This model, trained using the TRL framework, is designed for text generation tasks with a substantial context length of 32768 tokens. It specializes in generating responses to open-ended questions and conversational prompts, making it suitable for interactive AI applications.

Loading preview...

Model Overview

The 18-Death/sq-bijection-atbash-ecqa is a 3.1 billion parameter language model developed by 18-Death. It is a fine-tuned model, specifically trained using the TRL (Transformers Reinforcement Learning) framework. The model supports a significant context window of 32768 tokens, allowing for processing and generating longer sequences of text.

Key Capabilities

  • Text Generation: Excels at generating coherent and contextually relevant text based on given prompts.
  • Conversational AI: Demonstrated capability in responding to open-ended questions and engaging in conversational exchanges, as shown in its quick start example.
  • Fine-tuned Performance: Benefits from the SFT (Supervised Fine-Tuning) training procedure, enhancing its ability to follow instructions and generate desired outputs.

Training Details

The model was trained using the SFT method. The development leveraged several key 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 question-answering systems.
  • Creative content generation.
  • Chatbot development where engaging and extended responses are beneficial.