Rust Sun

vigos's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 27 days ago

Running on Zero

2.02k

2.02k

F5-TTS

🗣

F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)

liked a Space 28 days ago

Running on CPU Upgrade

235

235

Agent Leaderboard

💬

Ranking of LLMs for agentic tasks

updated a Space 28 days ago

Sleeping

First Agent Template

⚡

Fetch current time in a timezone and generate images

liked a dataset about 2 months ago

cais/hle

Viewer • Updated 26 days ago • 2.7k • 7.1k • 271

liked a model 2 months ago

cognitivecomputations/Dolphin3.0-Llama3.1-8B

Updated Jan 5 • 4.28k • 154

liked a Space 2 months ago

Running

708

708

UGI Leaderboard

📢

Display UGI Leaderboard data in a searchable table

liked a Space 3 months ago

Running

532

532

Scaling test-time compute

📈

Enhance math problem solving by scaling test-time compute

liked a model 4 months ago

jackboyla/glirel-large-v0

Updated Jan 8 • 15

liked a dataset 4 months ago

microsoft/orca-agentinstruct-1M-v1

Viewer • Updated Nov 1, 2024 • 1.05M • 9.21k • 431

liked 2 models 4 months ago

nomic-ai/nomic-embed-vision-v1.5

Image Feature Extraction • Updated Jan 16 • 41.7k • 149

nvidia/NV-Embed-v2

Feature Extraction • Updated 17 days ago • 331k • 394

liked a Space 4 months ago

Running

169

169

GLiNER-medium-v2.1, zero-shot NER

💻

Identify key entities in text

liked 3 models 4 months ago

ali-vilab/In-Context-LoRA

Text-to-Image • Updated Dec 17, 2024 • 114k • • 566

fishaudio/fish-agent-v0.1-3b

Audio-to-Audio • Updated Nov 1, 2024 • 508 • 253

microsoft/OmniParser

Image-Text-to-Text • Updated Dec 2, 2024 • 2.63k • 1.64k

liked a Space 5 months ago

Running

5

5

Docs Scraper

📙

Scrape website content and save as Markdown

liked 2 models 5 months ago

ostris/OpenFLUX.1

Text-to-Image • Updated Oct 3, 2024 • 6.72k • 648

meta-llama/Meta-Llama-Guard-2-8B

Text Generation • Updated May 13, 2024 • 17.6k • 290

upvoted an article 5 months ago

view article

Article

How to build a custom text classifier without days of human labeling

By and 4 others •

Oct 17, 2024

• 55

reacted to reach-vb's post with 👍 5 months ago

view post

Post

5540

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)

🔥

16

16

👍

5

5

❤️

2

2

😎

1

1

👀

1

1

🚀

1

1

+

Reply