Joseph [open/acc] Pollack

Tonic's activity

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

updated a Space about 10 hours ago

Runtime error

6

🤳🏻

Phi 4

Microsoft's iconic Phi-4 model

updated a collection about 13 hours ago

cool models

Collection

7 items • Updated about 13 hours ago

liked a dataset about 13 hours ago

HumanLLMs/Human-Like-DPO-Dataset

Viewer • Updated Sep 23, 2024 • 10.9k • 253 • 40

upvoted a collection about 13 hours ago

Human-Like LLMs

Collection

4 items • Updated 1 day ago • 5

liked 2 models 1 day ago

llamaindex/vdr-2b-multi-v1

Image-Text-to-Text • Updated 1 day ago • 499 • 33

disham993/electrical-classification-ModernBERT-base

Text Classification • Updated 6 days ago • 41 • 3

upvoted a collection 1 day ago

Electrical Device Feedback Classification Models

Collection

The "Electrical Device Feedback Classification Models" collection contains models trained to classify customer feedback on electrical devices. • 5 items • Updated 6 days ago • 2

reacted to hexgrad's post with 👀 1 day ago

view post

Post

5387

📣 Looking for labeled, high-quality synthetic audio/TTS data 📣 Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.

If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.

What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ❤️

More details at hexgrad/Kokoro-82M#21

See translation

• 
• 
• 
• 13 replies

·

🔥

20

20

🚀

5

5

👀

2

2

+

Reply

upvoted 2 collections 2 days ago

TACO Models

Collection

This collection contains the best-performing TACO models based on LLaMA-3/Qwen2 and SigLIP/CLIP. • 3 items • Updated 22 days ago • 8

My Loras

Collection

loras i've made that are hosted here • 11 items • Updated about 1 hour ago • 5

liked a Space 2 days ago

Running on Zero

2

🌔

moondream2

a tiny vision language model

liked a model 2 days ago

vikhyatk/moondream2

Image-Text-to-Text • Updated 2 days ago • 111k • 877

upvoted a paper 2 days ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published 3 days ago • 176

upvoted a collection 2 days ago

Sa2VA model zoo

Collection

3 items • Updated 4 days ago • 20

liked a model 3 days ago

microsoft/phi-4-gguf

Text Generation • Updated 3 days ago • 3.72k • 39

New activity in zero-gpu-explorers/README 3 days ago

ZeroGPU Decorator does not work with gr.load()

#147 opened 3 days ago by

Tonic

liked 2 models 3 days ago

facebook/musicgen-stem-7cb

Updated Nov 25, 2024 • 2

facebook/wav2vec2-base-10k-voxpopuli-ft-sk

Automatic Speech Recognition • Updated Jul 6, 2021 • 12 • 1

liked a Space 3 days ago

Starting on L40S

133

🧬🧪🧬

Protein Genesis v2

AI service generating protein structures from user text

liked a model 3 days ago

IntelligentEstate/Tangu-3B-Qwenstar-Q8-GGUF

Text Generation • Updated about 17 hours ago • 29 • 2