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

upvoted a collection about 2 months ago

MiMo-V2.6

6 items • Updated 20 days ago • 140

upvoted 2 collections 3 months ago

Nemotron Post-Training Datasets

Collection of datasets used in the post-training phase of Nemotron Nano, Super, Ultra v3, Super 3.5 VL, and Lightning 3.5. • 64 items • Updated 19 days ago • 208

Inkling

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort. • 4 items • Updated Jul 27 • 72

upvoted a collection 4 months ago

LLaDA2.2

2 items • Updated 12 days ago • 14

upvoted a collection 6 months ago

Qwen3.6

4 items • Updated Apr 22 • 507

upvoted 2 collections 10 months ago

WeDLM

4 items • Updated 11 days ago • 19

Hy-MT1.5

混元翻译模型1.5版本 • 12 items • Updated 11 days ago • 59

upvoted 2 collections 11 months ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 28 items • Updated 11 days ago • 159

GLM-4.7

3 items • Updated Jan 19 • 71

upvoted 10 collections about 1 year ago

GLM-4.6

2 items • Updated Mar 2 • 54

LLaDA2.0

10 items • Updated 12 days ago • 44

QwQ

Qwen with Questions • 6 items • Updated Dec 31, 2025 • 101

Qwen3-Coder

5 items • Updated Dec 31, 2025 • 185

Qwen-Image

14 items • Updated Dec 31, 2025 • 125

Qwen3-VL

37 items • Updated Dec 31, 2025 • 795

Qwen3Guard

7 items • Updated Dec 31, 2025 • 73

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 213

Qwen3-Next

4 items • Updated Dec 31, 2025 • 186

DeepSeek-V3.1

3 items • Updated Mar 2 • 267

upvoted a collection over 1 year ago

🧩 July 2025 - Open works from the Chinese community

38 items • Updated Jan 9 • 8