Introduction of DeepHermes-ToolCalling-Specialist-Atropos
Model Details of DeepHermes-ToolCalling-Specialist-Atropos
DeepHermes Tool Calling Specialist - Atropos RL
Model Overview
The
DeepHermes Tool Calling Specialist - Atropos RL
model is an experimental artifact fine-tuned by Nous Research using our innovative open-source reinforcement learning framework—Atropos. This variant specifically improves the tool calling performance of the
DeepHermes 3 Llama-3.1 8B
model during its reasoning mode.
Note
: This model is intended as an experimental artifact and is not designed for broad, general-purpose use.
Atropos Open Source Framework
Atropos is Nous Research’s open-source Reinforcement Learning environment stack, designed to enhance various aspects of LLM functionalities through structured RL methodologies. We encourage contributions and exploration:
Evaluations on the Berkeley Function Calling benchmark demonstrate significant improvements in tool calling accuracy during reasoning mode, compared to its base model:
Benchmark
Base Accuracy
Atropos RL Accuracy
Improvement
Parallel
0.10
0.46
4.6x
Simple
0.21
0.5175
2.5x
These enhancements are due to RL fine-tuning specifically targeted at improving reasoning-based tool calling capabilities.
Eval set accuracy results:
Key Features
Improved Tool Calling in Reasoning Mode
: Reinforcement learning significantly boosts tool usage during complex reasoning tasks.
Active Open Source Community
: Contributions welcomed on the Atropos GitHub.
Upcoming SOTA RL Trainer
: A state-of-the-art open-source reinforcement learning trainer by Nous Research is coming soon.
Usage
This model supports multiple inference modes including:
Reasoning (Deep Thinking Mode)
Standard Chat/Instruction Mode
Structured JSON Outputs
Function Calling
Detailed documentation and example inference code are available:
Note: You must first place DeepHermes' reasoning system prompt, and then append your function calling system prompt after for it to do reasoning and tool calling simultaneously.
@misc{
title={DeepHermes Tool Calling Specialist - Atropos RL},
author={Teknium and Dakota Mahan and Roger Jin and Chen Guang and Jai Suphavadeeprasit and Jeffrey Quesnelle},
year={2025},
url={https://huggingface.co/NousResearch/DeepHermes-Tool-Calling-Specialist-Atropos-RL}
}
Community and Support
For questions, issues, or findings, please open issues or discussions in the respective GitHub repositories:
DeepHermes-ToolCalling-Specialist-Atropos huggingface.co is an AI model on huggingface.co that provides DeepHermes-ToolCalling-Specialist-Atropos's model effect (), which can be used instantly with this NousResearch DeepHermes-ToolCalling-Specialist-Atropos model. huggingface.co supports a free trial of the DeepHermes-ToolCalling-Specialist-Atropos model, and also provides paid use of the DeepHermes-ToolCalling-Specialist-Atropos. Support call DeepHermes-ToolCalling-Specialist-Atropos model through api, including Node.js, Python, http.
DeepHermes-ToolCalling-Specialist-Atropos huggingface.co is an online trial and call api platform, which integrates DeepHermes-ToolCalling-Specialist-Atropos's modeling effects, including api services, and provides a free online trial of DeepHermes-ToolCalling-Specialist-Atropos, you can try DeepHermes-ToolCalling-Specialist-Atropos online for free by clicking the link below.
NousResearch DeepHermes-ToolCalling-Specialist-Atropos online free url in huggingface.co:
DeepHermes-ToolCalling-Specialist-Atropos is an open source model from GitHub that offers a free installation service, and any user can find DeepHermes-ToolCalling-Specialist-Atropos on GitHub to install. At the same time, huggingface.co provides the effect of DeepHermes-ToolCalling-Specialist-Atropos install, users can directly use DeepHermes-ToolCalling-Specialist-Atropos installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
DeepHermes-ToolCalling-Specialist-Atropos install url in huggingface.co: