narcolepticchicken/speculative-proposer-v3-1.7b

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:May 7, 2026Architecture:Transformer Warm

narcolepticchicken/speculative-proposer-v3-1.7b is a 1.7 billion parameter causal language model, fine-tuned from Qwen/Qwen3-1.7B. This model is specifically designed for generating speculative proposals and creative text, leveraging its base architecture for efficient text generation. It was trained using the TRL framework and supports a context length of 32768 tokens, making it suitable for tasks requiring detailed and imaginative responses.

Loading preview...

Overview

This model, speculative-proposer-v3-1.7b, is a fine-tuned version of the Qwen/Qwen3-1.7B base model, developed by narcolepticchicken. It has been specifically trained using the TRL (Transformers Reinforcement Learning) framework to enhance its capabilities in generating speculative and creative text.

Key Capabilities

  • Speculative Text Generation: Optimized for producing imaginative and hypothetical content.
  • Efficient Performance: Built upon the 1.7 billion parameter Qwen3 architecture, offering a balance of performance and resource efficiency.
  • Extended Context Window: Supports a context length of 32768 tokens, allowing for more detailed and coherent long-form generations.

Training Details

The model underwent Supervised Fine-Tuning (SFT) using TRL version 1.3.0. It leverages Transformers 5.8.0, Pytorch 2.11.0, Datasets 4.8.5, and Tokenizers 0.22.2.

Good For

  • Generating creative narratives or hypothetical scenarios.
  • Applications requiring imaginative text completion or idea generation.
  • Exploring speculative fiction or brainstorming concepts.