Paul M

PSM24

·

AI & ML interests

None yet

Recent Activity

reacted to reach-vb's post with 👍 6 days 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 model 7 days ago

burner22/numbat

liked a model 11 days ago

nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

View all activity

Organizations

PSM24 's datasets 6

PSM24/g2-5v2

Viewer • Updated Oct 20, 2025 • 179 • 8

PSM24/g2-5-p-110

Viewer • Updated May 6, 2025 • 109 • 5

PSM24/gemini-2.5-pro-100x

Viewer • Updated May 6, 2025 • 100 • 21 • 8

PSM24/reason-14B-MATH500

Viewer • Updated Jan 8, 2025 • 500 • 15 • 1

PSM24/formatted-reasoning

Viewer • Updated Jan 8, 2025 • 118k • 14 • 1

PSM24/qwq-MATH500-94

Viewer • Updated Dec 25, 2024 • 94 • 12