social-post-explorers (Social Post Explorers)

posted an update 17 days ago

Post

677

# 🚀 Run Qwen3-TTS on Colab GPU or Locally

Run **Qwen3-TTS (Text-to-Speech & Voice Cloning)** with minimal effort. This setup is based on the official HF Space.

### 🔗 Links
* **Official Space:** Qwen/Qwen3-TTS
* **GitHub Repo:** https://github.com/seyf1elislam/qwen-tts-webui-notebook
* **Colab:** https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb

---

### 📓 Method 1: Google Colab (Fastest)
1. Open the https://github.com/seyf1elislam/qwen-tts-webui-notebook/blob/main/Qwen_TTS_(TTS_%26_Voice_Cloning)_Colab.ipynb.
2. Add your HF_TOKEN to Google Colab Secrets
3. Ensure you are on a **T4 GPU** runtime.
4. Run all cells. Use the gradio.live link to open the UI.

---

### 💻 Method 2: Local Installation
Requires an GPU. Uses uv for faster setup.

# 1. Install uv & Clone
pip install uv
git clone https://huggingface.co/spaces/Qwen/Qwen3-TTS && cd Qwen3-TTS

# 2. Setup Environment
uv venv
uv pip install -r requirements.txt

# 3. Auth & Run
uvx hf auth login
python app.py 
# UI available at: http://localhost:7860/

mmhamdy

posted an update 30 days ago

Post

3063

The new DeepSeek Engram paper is super fun! It also integrates mHC, and I suspect they're probably releasing all these papers to make the V4 report of reasonable length😄

Here's a nice short summary from Gemini

mrfakename

posted an update 2 months ago

Post

14145

Excited to share that I've joined the Hugging Face Fellows program! 🤗

Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! 🚀

fernandofernandes

authored 4 papers 2 months ago

Spectrum: Targeted Training on Signal to Noise Ratio

Paper • 2406.06623 • Published Jun 7, 2024 • 15

Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation

Paper • 2406.14971 • Published Jun 21, 2024

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit

Paper • 2506.06607 • Published Jun 7, 2025 • 2

LFM2 Technical Report

Paper • 2511.23404 • Published Nov 28, 2025 • 52

theainerd

posted an update 3 months ago

Post

4929

Hindi Speech to Text just crossed 20 million downloads. Grateful for everyone using it.

theainerd/Wav2Vec2-large-xlsr-hindi

nouamanetazi

posted an update 4 months ago

Post

4414

After training 𝐒𝐦𝐨𝐥𝐋𝐌𝟑 on 𝟑𝟖𝟒 𝐇𝟏𝟎𝟎𝐬 for nearly a month, I've come to realize something most people overlook: 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐦𝐚𝐤𝐞-𝐨𝐫-𝐛𝐫𝐞𝐚𝐤 𝐟𝐚𝐜𝐭𝐨𝐫 𝐢𝐧 𝐋𝐋𝐌 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠. 🔥

Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious 𝐍𝐂𝐂𝐋 𝐞𝐫𝐫𝐨𝐫𝐬, or when your expensive GPU cluster is running at 𝟔𝟎% 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲, the problem isn't your model. It's most probably a 𝐦𝐢𝐬𝐮𝐬𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐡𝐚𝐫𝐝𝐰𝐚𝐫𝐞. 🛠️

Questions that seemed simple but had no clear answers: Why is 𝐌𝐨𝐄 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐬𝐥𝐨𝐰𝐞𝐫 𝐭𝐡𝐚𝐧 𝐝𝐞𝐧𝐬𝐞 𝐦𝐨𝐝𝐞𝐥𝐬? Which 𝐍𝐂𝐂𝐋 𝐟𝐥𝐚𝐠𝐬 should we actually set? How often should we checkpoint without killing throughput?

That's why we built 𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤 📖: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐥𝐚𝐲𝐞𝐫 that most teams get wrong.

We validated real vs theoretical bandwidth across the entire stack: 𝐇𝐁𝐌𝟑 𝐡𝐢𝐭𝐭𝐢𝐧𝐠 𝟑 𝐓𝐁/𝐬, 𝐍𝐕𝐋𝐢𝐧𝐤 𝟒.𝟎 𝐫𝐞𝐚𝐜𝐡𝐢𝐧𝐠 𝟕𝟖𝟔 𝐆𝐁/𝐬, 𝐏𝐂𝐈𝐞 𝐆𝐞𝐧𝟒 𝐚𝐭 𝟏𝟒.𝟐 𝐆𝐁/𝐬. Then we ran collective operations across 𝟏𝟐𝟖 𝐆𝐏𝐔𝐬 (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from 𝟒𝟖𝟎 𝐆𝐁/𝐬 on a single node to 𝟑𝟐𝟎-𝟑𝟓𝟎 𝐆𝐁/𝐬 across 16 nodes.

If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.

𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤: https://lnkd.in/e5MKXUHS

Shared with ❤️ by the HuggingFace team

mrfakename

posted an update 4 months ago

Post

6245

Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.

Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.

Will probably kick off a new run later with some settings tweaked.

Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo

(Turn 🔊 on to hear audio samples)

5 replies

·

arjunguha

authored 3 papers 5 months ago

xiaotianhan

authored a paper 6 months ago

InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

Paper • 2508.05731 • Published Aug 7, 2025 • 27

seyf1elislam

posted an update 6 months ago

Post

427

🚀 Run <14B, 12B, 8B… LLMs **for FREE** on Google Colab (15GB VRAM GPU)

🔗 Repo: https://github.com/seyf1elislam/LocalLLM_OneClick_Colab

📌 How to Use

1. Open the notebook → Click “Open in Colab” and enable GPU mode.
2. Enter model details → Provide the Hugging Face repo name & quantization type.

* Example: unsloth/Qwen3-8B-GGUF with quant Q5_k_m
3. Run all cells → Wait 1–3 minutes. You'll get a link to the GUI & API (OpenAI-compatible).

💡 Yes, it’s really free. Enjoy! ✨

---

📝 Supported Models (examples)

* Qwen3 14B** → Q5_k_m, Q4_k_m
* Qwen3 8B** → Q8_0
* Nemo 12B → Q6_k, Q5_k_m
* Gemma3 12B → Q6_k, Q5_k_m

---

💻 Available Notebooks

1. KoboldCpp(⭐⭐⭐ Recommended – faster setup & inference)
🔗 https://github.com/seyf1elislam/LocalLLM_OneClick_Colab/blob/main/awesome_koboldcpp_notebook.ipynb
2. TextGen-WebUI(⭐⭐ Recommended)
🔗 https://github.com/seyf1elislam/LocalLLM_OneClick_Colab/blob/main/Run_any_gguf_model_in_TextGen_webui.ipynb

merterbak

posted an update 6 months ago

Post

4736

OpenAI is now open again! Check out OpenAI’s brand new gpt‑oss‑20b model hosted on ZeroGPU 🤗

merterbak/gpt-oss-20b-demo

haritzpuerto

authored 2 papers 7 months ago

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

Paper • 2506.15674 • Published Jun 18, 2025 • 2

C-SEO Bench: Does Conversational SEO Work?

Paper • 2506.11097 • Published Jun 6, 2025 • 2

Smooke

in social-post-explorers/README 7 months ago

Request to post

➕ 2

17

#36 opened almost 2 years ago by

Walmart-the-bag

cbensimon

posted an update 8 months ago

Post

4323

🚀 ZeroGPU now supports PyTorch native quantization via torchao

While it hasn’t been battle-tested yet, Int8WeightOnlyConfig is already working flawlessly in our tests.

Let us know if you run into any issues — and we’re excited to see what the community will build!

import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_

pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)

@spaces.GPU
def generate(prompt: str):
    return pipeline(prompt).images[0]

5 replies

·

Social Post Explorers

AI & ML interests

Recent Activity

Spectrum: Targeted Training on Signal to Noise Ratio

Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit

LFM2 Technical Report

Substance Beats Style: Why Beginning Students Fail to Code with LLMs

SelfCodeAlign: Self-Alignment for Code Generation

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans

InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

C-SEO Bench: Does Conversational SEO Work?

Request to post

AI & ML interests

Recent Activity

Team members 854

social-post-explorers's activity

Request to post