18
Radio
📚
Generate image features and segmentations
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
liked
a Space
about 2 hours ago
nvidia/radio
upvoted
an
article
about 2 hours ago
Mastering Long Contexts in LLMs with KVPress
replied to
their
post
about 3 hours ago
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
Organizations
victor's activity
liked
a
Space
about 2 hours ago
upvoted
an
article
about 2 hours ago
Article
Mastering Long Contexts in LLMs with KVPress
By
and 1 other
•
•
59
replied to
their
post
about 3 hours ago
Specifically, the detailed status of individual spaces is now more difficult to understand visually than before. Whether it's private or not, whether you've liked it or not, whether it's RUNNING or not... etc.
Ok, I'll try to improve the contrast of it, should help?
replied to
their
post
about 3 hours ago
hope you like it!
updated
a
model
about 4 hours ago
Set base model
#3 opened about 4 hours ago
by
victor
reacted to
hexgrad's
post with 👍
about 15 hours ago
Post
1629
I wrote an article about G2P: https://hf.co/blog/hexgrad/g2p
G2P is an underrated piece of small TTS models, like offensive linemen who do a bunch of work and get no credit.
Instead of relying on explicit G2P, larger speech models implicitly learn this task by eating many thousands of hours of audio data. They often use a 500M+ parameter LLM at the front to predict latent audio tokens over a learned codebook, then decode these tokens into audio.
Kokoro instead relies on G2P preprocessing, is 82M parameters, and thus needs less audio to learn. Because of this, we can cherrypick high fidelity audio for training data, and deliver solid speech for those voices. In turn, this excellent audio quality & lack of background noise helps explain why Kokoro is very competitive in single-voice TTS Arenas.
G2P is an underrated piece of small TTS models, like offensive linemen who do a bunch of work and get no credit.
Instead of relying on explicit G2P, larger speech models implicitly learn this task by eating many thousands of hours of audio data. They often use a 500M+ parameter LLM at the front to predict latent audio tokens over a learned codebook, then decode these tokens into audio.
Kokoro instead relies on G2P preprocessing, is 82M parameters, and thus needs less audio to learn. Because of this, we can cherrypick high fidelity audio for training data, and deliver solid speech for those voices. In turn, this excellent audio quality & lack of background noise helps explain why Kokoro is very competitive in single-voice TTS Arenas.
- 1 reply
liked
a
model
about 19 hours ago
liked
3
Spaces
1 day ago
upvoted
4
papers
1 day ago
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Paper
•
2501.17703
•
Published
•
50
s1: Simple test-time scaling
Paper
•
2501.19393
•
Published
•
88
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper
•
2502.01061
•
Published
•
149
The Differences Between Direct Alignment Algorithms are a Blur
Paper
•
2502.01237
•
Published
•
104
reacted to
oleggolev's
post with 🚀
1 day ago
Post
4272
🚀 Dobby-mini is out!
Last week, @SentientAGI released two demo models for the upcoming Dobby model family which we are building with your feedback: SentientAGI/dobby-mini-679af3ed45dfdd8c25e8112c
🔥 The two models (available as transformers and GGUF) are here:
- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B 😈
- SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B 😇
Fine-tuned from Llama-3.1-8B-Instruct while retaining benchmark performance, these personality-enhanced models are prime for building anything from AI companions and social agents to opinionated chatbots and content generators.
- 🦅 Pro-freedom
- 💸 Pro-crypto
- 💪 Opinionated and stand their ground
💻 Local Setup with Ollama:
- Written instructions: https://huggingface.co/blog/chrisaubin/hosting-dobby-mini
- Companion video: https://www.youtube.com/watch?v=b1rbtCgK2YA
🎆 Use via API on Fireworks for free!
- Unhinged: https://tinyurl.com/4h2c7tmv
- Leashed: https://tinyurl.com/2xjwsdxb
✌️ Try Dobby-mini via a Gradio demo:
- https://demo-dobby.sentient.xyz/
- No Internet search, ask it some personal questions!
Dobby-70B en route 😎
Last week, @SentientAGI released two demo models for the upcoming Dobby model family which we are building with your feedback: SentientAGI/dobby-mini-679af3ed45dfdd8c25e8112c
🔥 The two models (available as transformers and GGUF) are here:
- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B 😈
- SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B 😇
Fine-tuned from Llama-3.1-8B-Instruct while retaining benchmark performance, these personality-enhanced models are prime for building anything from AI companions and social agents to opinionated chatbots and content generators.
- 🦅 Pro-freedom
- 💸 Pro-crypto
- 💪 Opinionated and stand their ground
💻 Local Setup with Ollama:
- Written instructions: https://huggingface.co/blog/chrisaubin/hosting-dobby-mini
- Companion video: https://www.youtube.com/watch?v=b1rbtCgK2YA
🎆 Use via API on Fireworks for free!
- Unhinged: https://tinyurl.com/4h2c7tmv
- Leashed: https://tinyurl.com/2xjwsdxb
✌️ Try Dobby-mini via a Gradio demo:
- https://demo-dobby.sentient.xyz/
- No Internet search, ask it some personal questions!
Dobby-70B en route 😎
posted
an
update
1 day ago
Post
2618
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
- 5 replies
liked
a
Space
1 day ago
liked
a
dataset
3 days ago
liked
a
Space
3 days ago