fahrizalfarid

akahana

AI & ML interests

NLP

Recent Activity

upvoted an article 3 days ago

Reverse Engineering a $500M Mystery: From HashHop to Memory-Augmented Language Models

reacted to codelion's post with 🔥 3 days ago

Reverse Engineering a $500M Mystery: From HashHop to Memory-Augmented Language Models I wrote a deep dive into how Magic AI's 100M token context window might work, starting from their HashHop benchmark and building up to MALM - a Memory-Augmented Language Model. Key insight: treating each key as a single token enables perfect retrieval at unlimited context lengths. The article covers: - How HashHop works and why its perfect accuracy is suspicious - Building a tokenized solver that achieves 100% accuracy - Scaling to MALM for real code search tasks - Why this approach could handle 100M+ tokens Read the full article: https://huggingface.co/blog/codelion/reverse-engineering-magic-hashhop Try the model: https://huggingface.co/codelion/malm-165m Code: https://github.com/codelion/hash-hop

updated a model 8 days ago

akahana/indo-psikologi-sft

View all activity

Organizations

None yet

upvoted an article 3 days ago

Article

Reverse Engineering a $500M Mystery: From HashHop to Memory-Augmented Language Models

4 days ago

•

reacted to codelion's post with 🔥 3 days ago

Post

2945

Reverse Engineering a $500M Mystery: From HashHop to Memory-Augmented Language Models

I wrote a deep dive into how Magic AI's 100M token context window might work, starting from their HashHop benchmark and building up to MALM - a Memory-Augmented Language Model.

Key insight: treating each key as a single token enables perfect retrieval at unlimited context lengths.

The article covers:

- How HashHop works and why its perfect accuracy is suspicious
- Building a tokenized solver that achieves 100% accuracy
- Scaling to MALM for real code search tasks
- Why this approach could handle 100M+ tokens

Read the full article: https://huggingface.co/blog/codelion/reverse-engineering-magic-hashhop

Try the model: codelion/malm-165m

Code: https://github.com/codelion/hash-hop

1 reply

updated a model 8 days ago

akahana/indo-psikologi-sft

0.6B • Updated 8 days ago • 93

reacted to sagar007's post with 🔥 8 days ago

Post

4116

🚀 I built a Multimodal Vision-Language Model from using Gemma-270M + CLIP!

Just finished training my multimodal model on the full LLaVA-Instruct-150K dataset (157K samples) and wanted to share the results!

🔧 What I Built:
A vision-language model that can understand images and answer questions about them, combining:
- Google Gemma-3-270M (language)
- OpenAI CLIP ViT-Large/14 (vision)
- LoRA fine-tuning for efficiency

📊 Training Stats:
- 157,712 training samples (full LLaVA dataset)
- 3 epochs on A100 40GB
- ~9 hours training time
- Final loss: 1.333 training / 1.430 validation
- Only 18.6M trainable params (3.4% of 539M total)

📈 sagar007/multigemma
Benchmark Results:
- VQA Accuracy: 53.8%
- Works great for: animal detection, room identification, scene understanding

🔗 **Try it yourself:**
- 🤗 Model: sagar007/multigemma
- 🎮 Demo: https://huggingface.co/spaces/sagar007/Multimodal-Gemma
- 💻 GitHub: https://github.com/sagar431/multimodal-gemma-270m

Built with PyTorch Lightning + MLflow for experiment tracking. Full MLOps pipeline with CI/CD!

Would love to hear your feedback! 🙏

#multimodal #gemma #clip #llava #vision-language #pytorch