alanzhuly commited on
Commit
540546c
·
verified ·
1 Parent(s): 2e42dfa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -7
README.md CHANGED
@@ -119,23 +119,59 @@ OmniNeural’s design is tightly coupled with NPU hardware:
119
 
120
  ---
121
 
122
- ## **How to use** //TODO
123
 
124
- > ⚠️ Note: OmniNeural currently runs on Qualcomm NPUs (Snapdragon devices).
125
- > Apple NPU support is planned for the next release.
126
 
127
- **Install via Nexa-SDK:**
 
128
 
129
- ## **Links & Community** //TODO
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
 
131
  ## **License & Citation**
132
 
133
  ```bibtex
134
  @misc{
135
- title={OmniNeural: NPU-Optimized Multimodal Model for On-Device AI},
136
  author={Nexa AI},
137
  year={2025},
138
- primaryClass={cs.CV},
139
  url={https://huggingface.co/NexaAI/OmniNeural-4B},
140
  }
141
  ```
 
119
 
120
  ---
121
 
122
+ ## How to use
123
 
124
+ > ⚠️ **Hardware requirement:** OmniNeural-4B currently runs **only on Qualcomm NPUs** (e.g., Snapdragon-powered AIPC).
125
+ > Apple NPU support is planned next.
126
 
127
+ ### 1) Install Nexa-SDK
128
+ Download and follow the steps in Nexa's model page:
129
 
130
+ - **Windows on Arm (AIPC)**: [Download Nexa-SDK](https://sdk.nexa.ai/model)
131
+ - (Other platforms coming soon)
132
+
133
+ ### 2) Get an access token
134
+ Create a token in the Model Hub, then log in:
135
+
136
+ ```bash
137
+ nexa config set license '<access_token>'
138
+ ```
139
+
140
+ ### 3) Run the model
141
+ Running:
142
+
143
+ ```bash
144
+ nexa infer NexaAI/OmniNeural-4B
145
+ ```
146
+
147
+ /mic mode. Once the model is running, you can type below to record your voice directly in terminal
148
+ ```bash
149
+ > /mic
150
+ ```
151
+
152
+ For images and audio, simply drag your files into the command line. Remember to leave space between file paths.
153
+
154
+
155
+ ## Links & Community
156
+
157
+ [![Discord](https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white)](https://discord.com/invite/nexa-ai)
158
+
159
+ [![X (Twitter) Follow](https://img.shields.io/badge/Follow-@nexa_ai-111?logo=x&logoColor=white)](https://x.com/nexa_ai)
160
+
161
+ [![Website](https://img.shields.io/badge/Website-nexa.ai-0A84FF)](https://nexa.ai)
162
+
163
+ - **Issues / Feedback:** Use the **HF Discussions** tab or submit an issue in our discord or nexa-sdk github.
164
+ - **Roadmap & updates:** Follow us on X and Discord.
165
+
166
+ > If you want to see more **NPU-first, multimodal** releases on HF, please give our model a like.
167
 
168
  ## **License & Citation**
169
 
170
  ```bibtex
171
  @misc{
172
+ title={OmniNeural: World’s First NPU-aware Multimodal Model},
173
  author={Nexa AI},
174
  year={2025},
 
175
  url={https://huggingface.co/NexaAI/OmniNeural-4B},
176
  }
177
  ```