didula-wso2/qwen3_swe_local_ep4sft_16bit_vllm

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The didula-wso2/qwen3_swe_local_ep4sft_16bit_vllm is an 8 billion parameter Qwen3 model, developed by didula-wso2, and fine-tuned for specific applications. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for tasks requiring a robust language model with a 32768 token context length, offering efficient performance for its size.

Loading preview...

Model Overview

The didula-wso2/qwen3_swe_local_ep4sft_16bit_vllm is an 8 billion parameter Qwen3 model, developed by didula-wso2. It was fine-tuned from the didula-wso2/Qwen3-8B-rl530_with_think_knowledge_merged base model.

Key Characteristics

  • Architecture: Qwen3, 8 billion parameters.
  • Training Efficiency: This model was fine-tuned significantly faster using the Unsloth library in conjunction with Huggingface's TRL library.
  • Context Length: Supports a context window of 32768 tokens.

Intended Use

This model is suitable for applications that benefit from a Qwen3-based language model with 8 billion parameters, particularly where efficient training methods have been employed. Its fine-tuned nature suggests it is optimized for specific tasks, building upon its merged knowledge base.