19 6 9

Łael Al-Halawani

ljhwild

AI & ML interests

None yet

Recent Activity

replied to victor's post about 1 month ago

🙋 Calling all Hugging Face users! We want to hear from YOU! What feature or improvement would make the biggest impact on Hugging Face? Whether it's the Hub, better documentation, new integrations, or something completely different – we're all ears! Your feedback shapes the future of Hugging Face. Drop your ideas in the comments below! 👇

New activity about 1 month ago

jainr3/diffusiondb-pixelart:Poor quality

updated a model about 2 months ago

ljhwild/madlad400-3b-mt-Q6_K-GGUF

View all activity

Organizations

None yet

ljhwild's activity

replied to victor's post about 1 month ago

Let's add system requirements to models.
It’d be super helpful to require or at least suggest that AI models include system requirements, just like other software. Minimum and recommended specs, especially for inference with Hugging Face libraries, would make things easier. Hardware info is often hard to find, and not everyone has access to H100 clusters. Setting this as a standard would make models way more accessible.
discussion here

New activity in jainr3/diffusiondb-pixelart about 1 month ago

Poor quality

#1 opened about 1 month ago by

ljhwild

updated a model about 2 months ago

ljhwild/madlad400-3b-mt-Q6_K-GGUF

Translation • Updated Oct 15 • 8.92k

replied to clem's post about 2 months ago

I used to be so pro open source AI, until I saw what china is doing with open source AI. I'm sorry but the risk is just too great. If we can't cut them out, we shouldn't share things out in the open.

reacted to clem's post with ❤️ about 2 months ago

Post

4153

Open-source AI creates healthy competition in a field where natural tendencies lead to extreme concentration of power. Imagine a world where only one or two companies could build software. This is the biggest risk and ethical challenge of them all IMO. Let's fight this!

3 replies

reacted to m-ric's post with ❤️ about 2 months ago

Post

2268

💥 𝐋-𝐌𝐮𝐥: 𝐀𝐝𝐝𝐢𝐭𝐢𝐨𝐧-𝐎𝐧𝐥𝐲 𝐌𝐮𝐥𝐭𝐢𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧 𝐜𝐚𝐧 𝐬𝐥𝐚𝐬𝐡 𝐜𝐨𝐦𝐩𝐮𝐭𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐜𝐨𝐬𝐭𝐬 𝐛𝐲 𝟖𝟎%!

Microsoft researchers dropped a groundbreaking technique that could slash the energy use in transformer computations : their novel "linear-complexity multiplication" (L-Mul) algorithm approximates floating-point multiplication using energy-efficient integer addition instead of costly multiplications.

💡 Quick reminder on how floats are coded on 8 bits (FP8):
In the e4m3 FP8 standard, you encode a number as:
Sign (1 bit) | Exponent (4 bits) | Mantissa (3 bits)
Example: 0 (positive) | 1000 (8) | 101 (1/2 + 1/8 = 0.625)
Calculation: you add one to the mantissa, and multiply it by 2 power (the exponent - a bias term which is 7 for e4m3):

➡️ You get (1 + 0.625) × 2^(8-7) = 3.25

Now back to the paper. 𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:

⚡️ Multiplication is extremely energy-intensive compared to addition. For 32-bit operations, multiplication (3.7 pJ) uses 37x more energy than addition (0.1 pJ)!

🧮 Traditional floating-point multiplication go like (noting xm the mantissa and xe the exponent): Mul(x,y) = (1 + xm) · 2^xe · (1 + ym) · 2^ye = (1 + xm + ym + xm · ym) · 2^(xe+ye)

💡 L-Mul cleverly approximates this as: L-Mul(x,y) = (1 + xm + ym + 2^-l(m)) · 2^(xe+ye), eliminating the costly xm · ym term

🔧 l(m) term is adaptively set based on mantissa size for optimal accuracy

📊 Benchmarks on the Llama-3.1-8B-Instruct model show L-Mul preserves precision across various NLP tasks, with performance nearly identical to full BFloat16 precision

💬 Authors claim: "We can achieve the same model inference performance while reducing the energy cost of attention computations by 80%."

This breakthrough is still theoretical and would need implementation on dedicated hardware to confirm real-world gains, but it’s a really exciting path for more sustainable AI! 🌱

Read the paper here 👉 Addition is All You Need for Energy-efficient Language Models (2410.00907)