Open Reasoner Zero 7B GGUF

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

🌊 We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training focusing on scalability, simplicity and accessibility.

To enable broader participation in this pivotal moment we witnessed and accelerate research towards artificial general intelligence (AGI), we release our source code, parameter settings, training data, and model weights. Please refer to our paper for more insights.

What is GGUF?

Prompt template: Open Reasoner Zero

A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.
User: You must put your answer inside <answer> </answer> tags, i.e., <answer> answer here </answer>. And your final answer will be extracted automatically by the \\boxed{} tag.\nThis is the problem:
{{prompt}}
Assistant: <think>

Download & run with cnvrs on iPhone, iPad, and Mac!

• create & save Characters with custom system prompts & temperature settings
• download and experiment with any GGUF model you can find on HuggingFace!
  • or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
• make it your own with custom Theme colors
• powered by Metal ⚡️ & Llama.cpp, with haptics during response streaming!
• try it out yourself today, on Testflight!
  • if you already have the app, download Open Reasoner Zero 7B now!
  • cnvrsai:///models/search/hf?id=brittlewis12/Open-Reasoner-Zero-7B-GGUF
• follow cnvrs on twitter to stay up to date

Original Model Evaluation

Figure 1 | Evaluation performance of Open-Reasoner-Zero-{7B, 32B}. We report the average accuracy on the benchmark dataset for each question with 16 responses. Notably, Open-Reasoner-Zero-32B outperforms DeepSeek-R1-Zero-Qwen-32B on the GPQA Diamond benchmark while only requiring 1/30 of the training steps. We are continuing to scale up these RL settings until this preprint is released, as there is no sign of saturation.