didula-wso2/Qwen3-8B-rl350_with_think_knowledge_merged

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:May 16, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The didula-wso2/Qwen3-8B-rl350_with_think_knowledge_merged is an 8 billion parameter Qwen3 model developed by didula-wso2. This model was finetuned using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is based on a prior finetune from didula-wso2/Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllm, suggesting a focus on specialized knowledge or reasoning capabilities.

Loading preview...

Model Overview

This model, didula-wso2/Qwen3-8B-rl350_with_think_knowledge_merged, is an 8 billion parameter Qwen3-based language model developed by didula-wso2. It was finetuned from didula-wso2/Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllm, indicating a lineage focused on specific knowledge domains or reasoning tasks.

Key Characteristics

  • Base Model: Qwen3 architecture.
  • Parameter Count: 8 billion parameters.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which enabled 2x faster training.
  • License: Released under the Apache-2.0 license.

Potential Use Cases

Given its finetuning history from a model with "julia_codeforces_extended_with_thinksft" in its name, this model is likely optimized for:

  • Tasks requiring specialized knowledge or reasoning, potentially in areas related to programming (e.g., Julia) or competitive programming problem-solving.
  • Applications where efficient training and deployment of a Qwen3-based model are beneficial.