Duan Nguyen

ConAim

2 314

AI & ML interests

None yet

Recent Activity

liked a Space 5 days ago

huggingface/moe-blogpost

liked a model 6 days ago

kakaocorp/kanana-2-v-decide-3b-2611

liked a Space 6 days ago

hugging-apps/kanana-2-v-decide-3b

View all activity

Organizations

None yet

liked a Space 5 days ago

The Ultimate MoE Training Handbook

🧩

563

A hands-on guide to training Mixture-of-Experts models

liked a model 6 days ago

kakaocorp/kanana-2-v-decide-3b-2611

Zero-Shot Classification • 4B • Updated 3 days ago • 900 • 33

liked a Space 6 days ago

Kanana-2-v-decide-3b

⚖

Typed decision questions over text, JSON, or images

liked a model 8 days ago

abenzerps/Qwen-Image-2.1-Turbo-Quantized

Text-to-Image • 7B • Updated 8 days ago • 112k • 5.83k

liked a model 9 days ago

LiquidAI/d1-3B-MLX-fp16

Image-Text-to-Text • 3B • Updated 9 days ago • 1.6k • 6

liked a Space 11 days ago

Inflect v2 — Tiny Local TTS

🔊

119

Run complete 3.96M and 9.36M text-to-waveform models live.

liked a Space 12 days ago

Qwen Image 2.1 Realtime

⚡

226

Real-time t2i & editing with a Qwen-Image-2.1 2-step LoRA

liked a model 15 days ago

axiomofmind/Moss-image-nsfw-uncensored-lora

Text-to-Image • Updated 18 days ago • 76.4k • 830

liked a Space 15 days ago

MOSS-Image NSFW LoRA

🌘

18+ demo of the Moss-image NSFW uncensored LoRA

liked a Space 16 days ago

Ming-3.0-tts-0.5B

🎙

Multilingual TTS with voice cloning & voice design

liked a model 16 days ago

inclusionAI/Ming-3.0-tts-0.5B

Text-to-Speech • 1B • Updated 15 days ago • 14.2k • 223

liked 2 models 19 days ago

mradermacher/granite-speech-5.0-2b-i1-GGUF

2B • Updated 20 days ago • 1.82k • 2

ibm-granite/granite-speech-5.0-2b

Automatic Speech Recognition • 2B • Updated 5 days ago • 9.85k • 82

liked a model 21 days ago

datalab-to/indra-ocr

Image-to-Text • 1.25M • Updated 23 days ago • 8.45k • 524

liked a model 24 days ago

deepseek-ai/DeepSeek-V4.1-Flash-1017

Image-Text-to-Text • 763B • Updated 2 days ago • 349k • • 5.51k

liked a model 25 days ago

openbmb/MiniCPM-V-4.7-35B-A3B

Image-Text-to-Text • 35B • Updated 9 days ago • 704k • 1.12k

liked a model 27 days ago

LiquidAI/d1-3B

Image-Text-to-Text • 3B • Updated about 6 hours ago • 27.9k • 503

liked 2 Spaces 27 days ago

Vevo2

🎤

Zero-shot speech and singing conversion and TTS

SoulX-Singer

🎤

Zero-shot singing voice synthesis from a reference