zenlm/zen-omni
1
0
Fork 0
mirror of https://github.com/zenlm/zen-omni.git synced 2026-07-26 22:09:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleanup: refresh SKU links + tidy (#1)

Browse Source 
Rewrite dead HF links to live successors, refresh stale Zen4 / old Zen-3 chat lineups to current Zen5 canonical + Zen3 specialty, and refresh user-facing prose (attribution and base_model chains preserved).

Co-authored-by: zooqueen <worringantje@gmail.com>
This commit is contained in:
Hanzo Dev
2026-05-29 22:27:17 -07:00
committed by GitHub
co-authored by zooqueen
parent 1966771101
commit 99bdd609a1
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LLM.md
+3 -3
View File
@@ -7,7 +7,7 @@
## Project Overview
Zen Omni is a hypermodal language model for translation and audio generation, built on Qwen3-Omni-30B-A3B. It is part of the Zen LM model family by Hanzo AI.
Zen Omni is a hypermodal language model for translation and audio generation, built on -Omni-30B-A3B. It is part of the Zen LM model family by Hanzo AI.
### Key Specifications
@@ -132,7 +132,7 @@ Pipeline stages:
## Key Technologies
- **Qwen3-Omni**: Base multimodal architecture
- **-Omni**: Base multimodal architecture
- **ms-swift**: ModelScope fine-tuning framework
- **MuseTalk**: Neural lip synchronization (zen-dub)
- **Whisper**: Audio feature extraction
@@ -180,7 +180,7 @@ All files reference the same knowledge base. Updates here propagate to all AI sy
- pyproject.toml
### In Progress 🔄
- Downloading Qwen3-Omni-30B-A3B-Instruct weights (~66GB)
- Downloading -Omni-30B-A3B-Instruct weights (~66GB)
### Pending 📋
- Identity fine-tuning execution