Spaces:
Runtime error
Runtime error
| 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 🤖 Mistral-NeMo-Minitron Demo 🚀""" | |
| description = """nvidia/🤖Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. | |
| """ | |
| presentation1 = """Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/nemotron-mini-4b-instruct). | |
| Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. It is a fine-tuned version of [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base), which was pruned and distilled from [Mistral-NeMo 12B](https://huggingface.co/nvidia/Mistral-NeMo-12B-Base) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). The model was trained using a multi-stage SFT and preference-based alignment technique with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner). For details on the alignment technique, please refer to the [Nemotron-4 340B Technical Report](https://arxiv.org/abs/2406.11704). | |
| ### License | |
| [NVIDIA Community Model License](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct/blob/main/nvidia-community-model-license-aug2024.pdf)""" | |
| presentation2 = """ | |
| ### Model Architecture | |
| 🤖Nemotron-Mini-4B-Instruct uses a model embedding size of 3072, 32 attention heads, and an MLP intermediate dimension of 9216. It also uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). | |
| **Architecture Type:** Transformer Decoder (auto-regressive language model) | |
| **Network Architecture:** Nemotron-4 """ | |
| 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"] | |
| }} | |
| }}""" |