Lucas Silva PRO

YuLexuan30

39 5 39

AI & ML interests

None yet

Recent Activity

reacted to yanghaojin's post with 🚀 3 days ago

Fish Audio’s Drama 3 text-to-speech now runs locally on Apple silicon and DGX Spark with gbx-lm. 🎙️ https://huggingface.co/GreenBitAI/Drama-3-8bit-paged Real time on 64 GB Macs and up (2.6x), and it still runs on a 48 GB MacBook Pro: experts stream from the SSD Zero-shot voice cloning from a 5–30 s clip, and the cloned voice can speak other languages Multi-speaker dialogue, cues like [laughs] [whispering], 83 languages OpenAI-compatible /v1/audio/speech with streaming, no PyTorch needed Built with Fish Audio · community build · Fish Audio Community License

updated a model 7 days ago

YuLexuan30/balloonblowtopoph3

published a model 8 days ago

YuLexuan30/balloonblowtopoph3

View all activity

Organizations

reacted to yanghaojin's post with 🚀 3 days ago

Post

2,768

Fish Audio’s Drama 3 text-to-speech now runs locally on Apple silicon and DGX Spark with gbx-lm. 🎙️

GreenBitAI/Drama-3-8bit-paged

Real time on 64 GB Macs and up (2.6x), and it still runs on a 48 GB MacBook Pro: experts stream from the SSD
Zero-shot voice cloning from a 5–30 s clip, and the cloned voice can speak other languages
Multi-speaker dialogue, cues like [laughs] [whispering], 83 languages
OpenAI-compatible /v1/audio/speech with streaming, no PyTorch needed

Built with Fish Audio · community build · Fish Audio Community License

updated a model 7 days ago

YuLexuan30/balloonblowtopoph3

Updated 7 days ago

published a model 8 days ago

YuLexuan30/balloonblowtopoph3

Updated 7 days ago

liked a model 9 days ago

realrebelai/Fibo-2.0_GGUFs

8B • Updated 9 days ago • 5.8k • 6

reacted to Banaxi-Tech's post with 🔥 9 days ago

Post

4,244

Hi everyone
We at

saicr have found a very interesting "thing" we call ADN via interpretabillity. It appears on EVERY prompt sent to the model. More on that later.
Also I made a X account follow it for more updates:
@banaxitech

And KleinML:
@kleinmlai

Here's my website for Klein ML: https://kleinml.com/?ref=huggingface.co

4 replies

New activity in Comfy-Org/Fibo-2.0 11 days ago

Example workflow?

#1 opened 11 days ago by

YuLexuan30

New activity in black-forest-labs/flux-3-image-klein-comfy 15 days ago

sorry but this is best trash model😭🙏

👍 13

#8 opened 16 days ago by

darkenHUB

DISTILLED versus BASE: 8MP comparison

#25 opened 15 days ago by

Liquidmind111

reacted to mithulaartigala's post with 🔥 20 days ago

Post

4,632

I am LOVING HuggingFace Pro <3

7 replies

reacted to Parveshiiii's post with 🤗 23 days ago

Post

3,852

Most deepfake audio detectors are quietly cheating.

They don’t really listen to the speech — they just look at how long the embedding vector is. Once they figure that out, accuracy looks great on paper and falls apart in the wild.

AIRealNet-Audio was built to stop that shortcut.
It forces every feature onto the unit hypersphere (twice) so the model can only use direction, not magnitude. Trained on speech from 100+ different TTS and voice-cloning systems, plus real human recordings under heavy compression and noise.

The result is a detector that actually has to learn the artifacts instead of gaming the feature space.

Model: Modotte/AIRealNet-Audio

liked a Space about 1 month ago

Qwen3.8-27B-Uncensored

🔓

222

Uncensored Qwen3.8-27B, text and vision chat

New activity in Lightricks/LTX-2.5 2 months ago

Any chance for a bigger text encoder (e.g. Gemma 4 26b) for the next version?

👍 2

#62 opened 2 months ago by

kabachuha

liked a model 3 months ago

Lightricks/LTX-2.5

Image-to-Video • Updated 21 days ago • 2.44M • 10.1k

New activity in Kijai/LTX2.3_comfy 3 months ago

I'm not getting any speedup from int8 convrot on my 5-series card. Has anyone tried this?

#75 opened 3 months ago by

liuxingsyue

upvoted a changelog 3 months ago

Hugging Face Changelog

MCP Server Enhancements

Jul 22

• 251

reacted to SeaWolf-AI's post with 🚀 3 months ago

Post

5,164

A small gift for anyone building or studying foundation models.

Most "open" models hand you the weights and stop there. With Aether-7B-5Attn we wanted to hand over the whole thing — so you can actually learn from it, reproduce it, and build on it: the data recipe, the training code, every hyperparameter, the complete logs, and the intermediate checkpoints. All Apache-2.0, reproducible byte-for-byte.

What you can do with it:
🔁 Rebuild it from scratch, or fork the recipe for your own model
🔬 Study a real heterogeneous-attention MoE — 49 layers place 5 attention mechanisms on a 7×7 Latin square, arranged as a clean, attributable ablation
📈 Trace training dynamics across the released checkpoints (110k / 115k / 162k)

It's a modest 6.59B model, and an honest one — the limitations (no KV-cache in this build, small scale) are written right in the card. We're not claiming it's special. If any piece of it saves you time or teaches you something, that's exactly what we hoped for. 🤗

📖 Full write-up →
[blog] · https://huggingface.co/blog/FINAL-Bench/opensource-llm
📦 5 Attention Base · FINAL-Bench/Aether-7B-5Attn
🎯 5 Attention Instruct · FINAL-Bench/Aether-7B-5Attn-it
🚀 5 Attention Live demo · FINAL-Bench/Aether-Sovereign-AI
📦 7 Attention Base · https://huggingface.co/FINAL-Bench/Aether-7B-7Attn-base
📦 11 Attention Base · FINAL-Bench/Aether-6B-11Attn-base
🧬 Collection · https://huggingface.co/collections/FINAL-Bench/aether-foundation-model

#opensource #LLM #MoE #reproducibility #Apache2

5 replies

reacted to danielhanchen's post with 🚀 3 months ago

Post

6,974

Gemma 4 is now faster and much more accurate! 🚀

Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!

Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4