mduy1129/qwen3-8b-folc

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:May 25, 2026Architecture:Transformer Warm

mduy1129/qwen3-8b-folc is an 8 billion parameter causal language model fine-tuned from Qwen/Qwen3-8B. This model was trained using the TRL framework with Supervised Fine-Tuning (SFT). It is designed for general text generation tasks, leveraging the base capabilities of the Qwen3 architecture.

Loading preview...

Model Overview

mduy1129/qwen3-8b-folc is an 8 billion parameter language model derived from the Qwen/Qwen3-8B base model. It has been fine-tuned using the TRL (Transformers Reinforcement Learning) library, specifically employing a Supervised Fine-Tuning (SFT) approach.

Key Characteristics

  • Base Model: Qwen/Qwen3-8B, a robust 8B parameter architecture.
  • Training Method: Fine-tuned with Supervised Fine-Tuning (SFT) using the TRL framework.
  • Context Length: Supports a context length of 32768 tokens, enabling processing of longer inputs.

Intended Use Cases

This model is suitable for a variety of text generation tasks, building upon the general capabilities of the Qwen3-8B foundation. Developers can leverage it for applications requiring coherent and contextually relevant text outputs, such as:

  • General text generation: Creating responses to prompts, completing sentences, or generating creative content.
  • Instruction following: Responding to user queries in a conversational or task-oriented manner, as demonstrated by the quick start example.

Technical Details

The model was developed using specific versions of popular machine learning frameworks:

  • PEFT: 0.19.1
  • TRL: 1.4.0
  • Transformers: 5.9.0
  • Pytorch: 2.10.0+cu128
  • Datasets: 4.8.5
  • Tokenizers: 0.22.2