Muhamad Hafizh's picture
1

Muhamad Hafizh

ujong16
ยท

AI & ML interests

None yet

Recent Activity

Organizations

None yet

ujong16's activity

reacted to Yehor's post with ๐Ÿ‘€ 20 days ago
reacted to hesamation's post with โค๏ธ 20 days ago
view post
Post
2698
What, How, Where, and How Well? This paper reviews test-time scaling methods and all you need to know about them:
> parallel, sequential, hybrid, internal scaling
> how to scale (SFT, RL, search, verification)
> metrics and evals of test-time scaling

๐Ÿ”—paper: What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models (2503.24235)

If you want to learn what inference-time compute scaling is @rasbt has a great blog post on that:
https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling
reacted to vincentg64's post with ๐Ÿ”ฅ 20 days ago
view post
Post
2286
The Rise of Specialized LLMs for Enterprise -https://mltblog.com/3QXXE4I

In this article, I discuss the main problems of standard LLMs (OpenAI and the likes), and how the new generation of LLMs addresses these issues. The focus is on Enterprise LLMs.

LLMs with Billions of Parameters: Most of the LLMs still fall in that category. The first ones (ChatGPT) appeared around 2022, though Bert is an early precursor. Most recent books discussing LLMs still define them as transformer architecture with deep neural networks (DNNs), costly training, and reliance on GPUs. The training is optimized to predict the next tokens or missing tokens. However, this task is remotely relevant to what modern LLMs now deliver to the user, see here. Yet it requires time and intensive computer resources. Indeed, this type of architecture works best with billions or trillions of tokens. In the end, most of these tokens are noise, requiring smart distillation for performance improvement.

The main issues are:

โžก๏ธ Performance: Requires GPU and large corpuses as input data. Re-training is expensive. Hallucinations are still a problem. Fine-tuning is delicate (Blackbox). You need prompt engineering to get the best results. Mixtures of experts (multiple sub-LLMs, DeepSeek) is one step towards improving accuracy.

โžก๏ธ Cost: Besides the GPU costs, the pricing model charges by the token, incentivizing vendors to use models with billions of tokens.

Read full article describing more issues and how LLM 2.0 addresses them, at https://mltblog.com/3QXXE4I

More links:

- To receive latest updates: https://mltblog.com/4iTvQec
- About LLM 2.0: https://mltblog.com/4g2sKTv
- PowerPoint presentation: https://mltblog.com/43DYviE
- Our company website: https://mlt

reacted to openfree's post with ๐Ÿ”ฅ 20 days ago
view post
Post
8269
๐Ÿ”ฅ 'Open Meme Studio': Your Creative Meme Factory ๐ŸŽญโœจ

Hello everyone! Today I'm introducing 'Open Meme Studio', an amazing space where you can easily create and transform fun and original meme images. ๐Ÿš€

VIDraft/Open-Meme-Studio

๐ŸŽฏ Taking Meme Creation to the Next Level!
This application leverages the powerful Kolors model and IP-Adapter-Plus to upgrade your meme-making abilities. Go beyond simple image editing and experience a completely new meme world powered by AI!

๐Ÿ› ๏ธ Features You'll Love

๐Ÿ“ธ Transform and reinterpret existing meme templates
๐ŸŽญ Freely change expressions and poses
๐Ÿ‘“ Add props (sunglasses, hats, etc.)
๐Ÿž๏ธ Change backgrounds and composite characters
๐ŸŽจ Apply various artistic styles

๐Ÿ’ช Why 'Open Meme Studio' is So Effective

Fast Meme Generation: High-quality memes completed in seconds
Unlimited Creativity: Completely different results just by changing prompts
User-Friendly Interface: Simple prompt input and image upload is all you need
Fine-tuned Control: Adjust how much of the original image characteristics to preserve
Advanced User Options: Freely set seed values, resolution, number of steps, and more

๐Ÿš€ Streamlined Meme Creation Process
Tasks that previously required complex tools like Photoshop can now be accomplished with just a few simple prompts. Experience intuitive image manipulation through text commands.

๐ŸŒˆ Effective Prompt Examples

๐Ÿ˜Ž "sunglass" - Add cool sunglasses to your character
๐Ÿ”๏ธ "background alps" - Change the background to Alpine mountains
๐Ÿ’ƒ "dancing" - Transform your character into a dancing pose
๐Ÿ˜ "smile" - Change to a smiling expression
๐ŸŽฎ "with Pikachu" - Create a scene with Pikachu
๐ŸŽจ "3d style" - Convert to 3D style

๐Ÿ”— Join Our Community
For more meme creation tips and interaction with other users, join our Discord!
https://discord.gg/openfreeai

Start creating unique memes that will shake up social media with 'Open Meme Studio' right now! ๐Ÿš€๐Ÿ’ฏ It's time for your meme
  • 3 replies
ยท
reacted to ginipick's post with ๐Ÿ”ฅ 20 days ago
view post
Post
7838
๐Ÿฏ Open Ghibli Studio: Transform Your Photos into Ghibli-Style Artwork! โœจ

Hello AI enthusiasts! ๐Ÿ™‹โ€โ™€๏ธ Today I'm introducing a truly magical project: Open Ghibli Studio ๐ŸŽจ

ginigen/FLUX-Open-Ghibli-Studio

๐ŸŒŸ What Can It Do?
Upload any regular photo and watch it transform into a beautiful, fantastical image reminiscent of Hayao Miyazaki's Studio Ghibli animations! ๐Ÿž๏ธโœจ

๐Ÿ”ง How Does It Work?

๐Ÿ“ธ Upload your photo
๐Ÿค– Florence-2 AI analyzes the image and generates a description
โœ๏ธ "Ghibli style" is added to the description
๐ŸŽญ Magic transformation happens using the FLUX.1 model and Ghibli LoRA!

โš™๏ธ Customization Options
Want more control? Adjust these in the advanced settings:

๐ŸŽฒ Set a seed (for reproducible results)
๐Ÿ“ Adjust image dimensions
๐Ÿ” Guidance scale (prompt adherence)
๐Ÿ”„ Number of generation steps
๐Ÿ’ซ Ghibli style intensity

๐Ÿš€ Try It Now!
Click the "Transform to Ghibli Style" button below to create your own Ghibli world! Ready to meet Totoro, Howl, Sophie, or Chihiro? ๐ŸŒˆ

๐ŸŒฟ Note: For best results, use clear images. Nature landscapes, buildings, and portraits transform especially well!
๐Ÿ’– Enjoy the magical transformation! Add some Ghibli magic to your everyday life~ โœจ