ChuGyouk/Arguinas-Qwen3-8B-100p-lr5e6

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:May 28, 2026Architecture:Transformer Warm

ChuGyouk/Arguinas-Qwen3-8B-100p-lr5e6 is an 8 billion parameter language model fine-tuned by ChuGyouk, based on the unsloth/Qwen3-8B architecture. This model was trained using SFT (Supervised Fine-Tuning) with TRL, focusing on general text generation tasks. It leverages a 32768 token context length, making it suitable for applications requiring processing longer inputs and generating coherent, extended responses. Its fine-tuning process aims to enhance its conversational and generative capabilities.

Loading preview...

Overview

ChuGyouk/Arguinas-Qwen3-8B-100p-lr5e6 is an 8 billion parameter language model developed by ChuGyouk. It is a fine-tuned variant of the unsloth/Qwen3-8B base model, specifically trained using Supervised Fine-Tuning (SFT) with the TRL (Transformer Reinforcement Learning) library. This model is designed for general text generation tasks, offering a substantial 32768 token context window.

Key Capabilities

  • General Text Generation: Capable of generating diverse and coherent text based on user prompts.
  • Fine-tuned Performance: Benefits from SFT to improve its conversational and response generation quality.
  • Extended Context Window: Supports a 32768 token context length, allowing for processing and generating longer sequences of text.

Training Details

The model underwent SFT using TRL, with specific framework versions including TRL 0.24.0, Transformers 4.57.6, Pytorch 2.10.0+cu130, and Datasets 4.3.0. The training process can be visualized via Weights & Biases, as indicated in the original repository. This fine-tuning aims to optimize its performance for interactive and generative applications.