SeongryongJung/qwen3-8b-tooluse-rlsd-ema005

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 2, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

SeongryongJung/qwen3-8b-tooluse-rlsd-ema005 is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. This model specializes in tool use, having been optimized with RLSD (Reinforcement Learning from Simulated Dialog) on a dedicated tooluse dataset. It demonstrates strong performance in tool-related tasks, making it suitable for applications requiring function calling and external API interaction.

Loading preview...

Model Overview

SeongryongJung/qwen3-8b-tooluse-rlsd-ema005 is an 8 billion parameter model derived from the Qwen3-8B architecture. It has undergone specific fine-tuning using Reinforcement Learning from Simulated Dialog (RLSD) with an EMA of 0.05, focusing exclusively on the tooluse split of a dataset.

Key Capabilities

  • Tool Use Optimization: Specifically fine-tuned for tasks involving tool interaction and function calling.
  • RLSD Training: Utilizes Reinforcement Learning from Simulated Dialog to enhance its ability to effectively use tools.
  • Performance Metrics: Achieved a peak validation performance of 66.73% on the val-aux/tooluse/reward/mean@16 metric during training, indicating proficiency in tool-related scenarios.

Intended Use Cases

This model is particularly well-suited for applications that require:

  • Function Calling: Interacting with external APIs or functions based on user prompts.
  • Automated Task Execution: Developing agents that can leverage tools to complete complex tasks.
  • Tool-Augmented Language Generation: Enhancing language models with the ability to perform actions through tools.

Finetunes
1 models