thehekimoghlu commited on
Commit
914ac42
·
verified ·
1 Parent(s): 7986fa3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -5,9 +5,9 @@ language:
5
  pipeline_tag: any-to-any
6
  ---
7
 
8
- ## **Spectra-561B-27B-512E: Model Overview**
9
 
10
- **Omnira Spectra-561B-27B-512E** is a state-of-the-art open-source omni-modal model developed by Omnira's Artificial Intelligence Team. Designed for **real-time audio-visual interaction**, it integrates text, image, video, and audio processing into a single, unified framework.
11
  ---
12
 
13
  ### **Core Architecture**
@@ -48,7 +48,7 @@ The model utilizes a massive **Mixture-of-Experts (MoE)** structure that balance
48
  | --- | --- |
49
  | **Total Parameters** | 561B |
50
  | **Activated Parameters** | 27B |
51
- | **Expert Configuration** | 512 Routed Experts |
52
  | **Context Window** | 128K tokens |
53
  | **Primary Tasks** | Audio, Visual, Text, Video-Continuation |
54
 
@@ -73,20 +73,20 @@ Due to its massive scale (561B), Spectra requires multi-node clusters or high-me
73
  ```python
74
  from spectra_omni import SpectraModel
75
 
76
- model = SpectraModel.from_pretrained("thenexthub/Spectra-561B-27B-512E")
77
  # Seamlessly process audio, image, and text inputs
78
 
79
  ```
80
 
81
  ## License Agreement
82
 
83
- The **model weights** are released under the **MIT License**. This license does not grant any rights to use Omnira trademarks or patents.
84
 
85
  ## Citation
86
 
87
  ```
88
  @misc{omnira2026spectra,
89
- title={Spectra-561B-27B-512E: Unified Omni-modal Intelligence},
90
  author={Omnira},
91
  year={2026},
92
  url={https://github.com/theomnira/Spectra-Omni},
 
5
  pipeline_tag: any-to-any
6
  ---
7
 
8
+ ## **Spectra-561B-27B-768E: Model Overview**
9
 
10
+ **Omnira Spectra-561B-27B-768E** is a state-of-the-art open-source omni-modal model developed by Omnira's Artificial Intelligence Team. Designed for **real-time audio-visual interaction**, it integrates text, image, video, and audio processing into a single, unified framework.
11
  ---
12
 
13
  ### **Core Architecture**
 
48
  | --- | --- |
49
  | **Total Parameters** | 561B |
50
  | **Activated Parameters** | 27B |
51
+ | **Expert Configuration** | 512 Routed; 256 Zero Experts |
52
  | **Context Window** | 128K tokens |
53
  | **Primary Tasks** | Audio, Visual, Text, Video-Continuation |
54
 
 
73
  ```python
74
  from spectra_omni import SpectraModel
75
 
76
+ model = SpectraModel.from_pretrained("thenexthub/Spectra-561B-27B-768E")
77
  # Seamlessly process audio, image, and text inputs
78
 
79
  ```
80
 
81
  ## License Agreement
82
 
83
+ The **model weights** are released under the **Omnira License**. This license does not grant any rights to use Omnira trademarks or patents.
84
 
85
  ## Citation
86
 
87
  ```
88
  @misc{omnira2026spectra,
89
+ title={Spectra-561B-27B-768E: Unified Omni-modal Intelligence},
90
  author={Omnira},
91
  year={2026},
92
  url={https://github.com/theomnira/Spectra-Omni},