Spaces:
Running
on
Zero
Running
on
Zero
| joinus = """ | |
| ## Join us : | |
| 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [](https://discord.gg/qdfnvSPcqP) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗 | |
| """ | |
| title = """# 🙋🏻♂️Welcome to Tonic's 🤖 OpenReasoning-Nemotron-14B Demo 🚀""" | |
| description = """nvidia/🤖OpenReasoning-Nemotron-14B is a reasoning model that is post-trained for reasoning about math, code and science solution generation. It demonstrates exceptional performance across challenging reasoning benchmarks. | |
| """ | |
| presentation1 = """Try this model on [Hugging Face](https://huggingface.co/nvidia/OpenReasoning-Nemotron-14B). | |
| OpenReasoning-Nemotron-14B is a large language model (LLM) which is a derivative of Qwen2.5-14B-Instruct. It is a reasoning model that is post-trained for reasoning about math, code and science solution generation. This model has been evaluated with up to 64K output tokens. The OpenReasoning model is available in the following sizes: 1.5B, 7B, 14B and 32B. | |
| The models demonstrate exceptional performance across a suite of challenging reasoning benchmarks. The 14B model consistently sets new state-of-the-art records for its size class, achieving: | |
| - **AIME24**: 87.8% pass@1 | |
| - **AIME25**: 82.0% pass@1 | |
| - **HMMT Feb 25**: 71.2% pass@1 | |
| - **LiveCodeBench v6**: 67.9% pass@1 | |
| - **GPQA**: 71.6% pass@1 | |
| - **MMLU-PRO**: 77.5% pass@1 | |
| ### License | |
| Creative Commons Attribution 4.0 International License (CC-BY-4.0) with Apache 2.0 License""" | |
| presentation2 = """ | |
| ### Model Architecture | |
| 🤖OpenReasoning-Nemotron-14B uses a dense decoder-only Transformer architecture based on Qwen2.5-14B-Instruct. It has 14B model parameters and supports up to 64,000 output tokens for extended reasoning chains. | |
| **Architecture Type:** Dense decoder-only Transformer model | |
| **Network Architecture:** Qwen2.5-14B-Instruct | |
| **Model Size:** 14B parameters | |
| **Max Output Tokens:** 64,000 """ | |
| customtool = """{ | |
| "name": "custom_tool", | |
| "description": "A custom tool defined by the user", | |
| "parameters": { | |
| "type": "object", | |
| "properties": { | |
| "param1": { | |
| "type": "string", | |
| "description": "First parameter of the custom tool" | |
| }, | |
| "param2": { | |
| "type": "string", | |
| "description": "Second parameter of the custom tool" | |
| } | |
| }, | |
| "required": ["param1"] | |
| } | |
| }""" | |
| example = """{{ | |
| "name": "get_current_weather", | |
| "description": "Get the current weather in a given location", | |
| "parameters": {{ | |
| "type": "object", | |
| "properties": {{ | |
| "location": {{ | |
| "type": "string", | |
| "description": "The city and state, e.g. San Francisco, CA" | |
| }}, | |
| "unit": {{ | |
| "type": "string", | |
| "enum": ["celsius", "fahrenheit"] | |
| }} | |
| }}, | |
| "required": ["location"] | |
| }} | |
| }}""" |