aohenduo's picture

aohenduo

chenduo

AI & ML interests

None yet

Recent Activity

Organizations

None yet

chenduo's activity

New activity in shenzhi-wang/Llama3.1-70B-Chinese-Chat about 2 months ago

Will there be multimodal support?

#10 opened about 2 months ago by
chenduo
liked a Space 2 months ago
reacted to reach-vb's post with ๐Ÿ‘ 2 months ago
view post
Post
5441
Multimodal Ichigo Llama 3.1 - Real Time Voice AI ๐Ÿ”ฅ

> 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 โšก

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)
reacted to clem's post with ๐Ÿ‘ 5 months ago
view post
Post
2497
This is the week of small AI language models!
ยท
New activity in ChaoticNeutrals/RPMix-4x7B-MoE 8 months ago

Quantization error

2
#1 opened 8 months ago by
chenduo