Hugging Face's logo
Arham Sanzid 's picture
2 1 21

Arham Sanzid

Sanzid
·

AI & ML interests

None yet

Recent Activity

upvoted a collection about 2 months ago
Open LLM Leaderboard best models ❤️‍🔥
reacted to reach-vb's post with ❤️ 4 months ago
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: https://huggingface.co/spaces/jan-hq/Ichigo-llama3.1-s-instruct)
liked a Space 10 months ago
jbilcke-hf/ai-comic-factory
View all activity

Organizations

None yet

Sanzid's activity

upvoted a collection about 2 months ago
reacted to reach-vb's post with ❤️ 4 months ago
view post
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)
liked a Space 10 months ago
New activity in mitkox/gemma-2b-dpo-uncensored-4bit 11 months ago

please convert to gguf

2
#1 opened 11 months ago by deleted
liked 11 models over 1 year ago
liked a Space over 1 year ago
liked 2 models almost 2 years ago
liked a model about 2 years ago
liked a Space about 2 years ago