Alibaba_Speech_Lab_SG PRO

alibabasglab

AI & ML interests

speech enhancement, separation, and codec

Recent Activity

Organizations

Alibaba-PAI's profile picture

alibabasglab's activity

posted an update 3 days ago
posted an update 8 days ago
reacted to their post with 🤗❤️🚀🔥 10 days ago
posted an update 10 days ago
reacted to their post with 🤝❤️🔥 13 days ago
reacted to prithivMLmods's post with 🔥 13 days ago
view post
Post
3061
ChemQwen-vL [ Qwen for Chem Vision ] 🧑🏻‍🔬

🧪Model : prithivMLmods/ChemQwen-vL

📝ChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/

📒Colab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju

Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/

🤗: @prithivMLmods
  • 1 reply
·
replied to prithivMLmods's post 13 days ago
reacted to m-ric's post with 👀 13 days ago
view post
Post
1192
𝗠𝗶𝗻𝗶𝗠𝗮𝘅'𝘀 𝗻𝗲𝘄 𝗠𝗼𝗘 𝗟𝗟𝗠 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝗖𝗹𝗮𝘂𝗱𝗲-𝗦𝗼𝗻𝗻𝗲𝘁 𝗹𝗲𝘃𝗲𝗹 𝘄𝗶𝘁𝗵 𝟰𝗠 𝘁𝗼𝗸𝗲𝗻𝘀 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗹𝗲𝗻𝗴𝘁𝗵 💥

This work from Chinese startup @MiniMax-AI introduces a novel architecture that achieves state-of-the-art performance while handling context windows up to 4 million tokens - roughly 20x longer than current models. The key was combining lightning attention, mixture of experts (MoE), and a careful hybrid approach.

𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:

🏗️ MoE with novel hybrid attention:
‣ Mixture of Experts with 456B total parameters (45.9B activated per token)
‣ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers

🏆 Outperforms leading models across benchmarks while offering vastly longer context:
‣ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
‣ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)

🔬 Technical innovations enable efficient scaling:
‣ Novel expert parallel and tensor parallel strategies cut communication overhead in half
‣ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)

🎯 Thorough training strategy:
‣ Careful data curation and quality control by using a smaller preliminary version of their LLM as a judge!

Overall, not only is the model impressive, but the technical paper is also really interesting! 📝
It has lots of insights including a great comparison showing how a 2B MoE (24B total) far outperforms a 7B model for the same amount of FLOPs.

Read it in full here 👉 MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users 👉 MiniMaxAI/MiniMax-Text-01
reacted to Tonic's post with 🔥 13 days ago
view post
Post
1494
🙋🏻‍♂️ Hey there folks ,

Facebook AI just released JASCO models that make music stems .

you can try it out here : Tonic/audiocraft

hope you like it
reacted to ariG23498's post with 🚀 13 days ago
reacted to singhsidhukuldeep's post with 🚀 13 days ago
view post
Post
1112
Breaking News: LinkedIn's Content Search Engine Gets a Powerful Semantic Upgrade!

Excited to share insights about LinkedIn's innovative approach to content search, recently detailed in a groundbreaking paper by their Mountain View team. This advancement represents a significant shift from traditional keyword-based search to semantic understanding.

>> Technical Architecture

The new search engine employs a sophisticated two-layer architecture:

Retrieval Layer
- Token Based Retriever (TBR) for exact keyword matching
- Embedding Based Retriever (EBR) using a two-tower model with multilingual-e5 embeddings
- Pre-computed post embeddings stored in a dedicated embedding store for efficient retrieval

Multi-Stage Ranking
- L1 Stage: Initial filtering using a lightweight model
- L2 Stage: Advanced ranking with complex features including:
- Query-post semantic matching
- Author reputation analysis
- User engagement metrics
- Content freshness evaluation

>> Performance Improvements

The system has achieved remarkable results:
- 10%+ improvement in both on-topic rate and long-dwell metrics
- Enhanced ability to handle complex natural language queries
- Significant boost in sitewide engagement

This advancement enables LinkedIn to better serve complex queries like "how to ask for a raise?" while maintaining high performance at scale. The system intelligently balances between exact keyword matching and semantic understanding, ensuring optimal results for both navigational and conceptual searches.

What impresses me most is how the team solved the scale challenge - processing billions of posts efficiently using pre-computed embeddings and approximate nearest neighbor search. This is enterprise-scale AI at its finest.
reacted to Xenova's post with 🔥 13 days ago
view post
Post
3667
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon!
👉 npm i kokoro-js 👈

Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX

You can get started in just a few lines of code!
import { KokoroTTS } from "kokoro-js";

const tts = await KokoroTTS.from_pretrained(
  "onnx-community/Kokoro-82M-ONNX",
  { dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);

const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
  { voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");

Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! 🤗

The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! 🤯
·
reacted to AdinaY's post with 👍 13 days ago
reacted to RudeBoi's post with 👀 13 days ago
view post
Post
1091
Can someone please explain to me why I am getting this error message? Please see the attached. I subscribe to the pro account and I am still getting this error message. Thanks.
·
reacted to nroggendorff's post with ❤️ 13 days ago
view post
Post
1244
maybe a page where you can find open orgs to get started in collaboration with hf. i see so many people that dont have a direction.


i dont have ulterior motives, so dont ask
  • 1 reply
·