3 15

aohenduo

chenduo

aohenduo

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

Qwen/Qwen2.5-VL-7B-Instruct

reacted to onekq's post with 🔥 9 days ago

🐋DeepSeek 🐋 is the real OpenAI 😯

liked a model about 1 month ago

deepseek-ai/DeepSeek-V3-Base

View all activity

Organizations

None yet

chenduo's activity

liked a model 4 days ago

Qwen/Qwen2.5-VL-7B-Instruct

Image-Text-to-Text • Updated 5 days ago • 90.1k • 251

reacted to onekq's post with 🔥 9 days ago

Post

4636

🐋DeepSeek 🐋 is the real OpenAI 😯

6 replies

liked 2 models about 1 month ago

deepseek-ai/DeepSeek-V3-Base

Updated 8 days ago • 24.3k • 1.48k

recursal/QRWKV6-32B-Instruct-Preview-v0.1

Text Generation • Updated 5 days ago • 1.47k • 67

liked a model 3 months ago

bartowski/MSM-MS-Cydrion-22B-GGUF

Text Generation • Updated Oct 4, 2024 • 781 • 6

New activity in shenzhi-wang/Llama3.1-70B-Chinese-Chat 3 months ago

Will there be multimodal support?

#10 opened 3 months ago by

chenduo

liked a Space 4 months ago

Runtime error

📚

Rebiber

reacted to reach-vb's post with 👍 4 months ago

Post

5498

Multimodal Ichigo Llama 3.1 - Real Time Voice AI 🔥

> WhisperSpeech X Llama 3.1 8B
> Trained on 50K hours of speech (7 languages)
> Continually trained on 45hrs 10x A1000s
> MLS -> WhisperVQ tokens -> Llama 3.1
> Instruction tuned on 1.89M samples
> 70% speech, 20% transcription, 10% text
> Apache 2.0 licensed ⚡

Architecture:
> WhisperSpeech/ VQ for Semantic Tokens
> Llama 3.1 8B Instruct for Text backbone
> Early fusion (Chameleon)

I'm super bullish on HomeBrew/ Jan and early fusion, audio and text, multimodal models!

(P.S. Play with the demo on Hugging Face: jan-hq/Ichigo-llama3.1-s-instruct)