Tetris is NP-Hard – http://
koaning.io https://
bit.ly/3XSJNkQ
#AI #MachineLearning #DeepLearning #LLMs #DataScience
CODE
-
Tetris Computational Complexity: Understanding NP-Hard Problem
By
–
-
Comparing LLM Context Windows for Coding and Research Tasks
By
–
Mainly Projects and higher rate limits. I feel like with 3.5 Opus it might get much more interesting. For projects it still depends: It might be good for research but for Coding it still has a very tiny context window. Gemini 2M for Workspace is more interesting in that sense
-
Building applications with Transformer agents and Llama 3.1
By
–
I made it using Transformers agents. You can find all the code under "files" in the Space, in file "
http://
app.py"
It uses llama3.1-70B, which would be too heavy to run on a consumer machine, but you can use our API as I did in the space! -
Advanced Retrieval-Augmented Generation Techniques Explained
By
–
Zain Hasan – Advanced Retrieval-Augmented Generation Techniques https://
bit.ly/3XSK0o8
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Fine-tune Datasets: Practical Guide with Code Examples
By
–
This blog covers in-depth guide with practical code examples which you can use to fine-tune your datasets or any OS datasets from HF hubs. Read the blog now using the link below:
-
MonsterAPIs: Interactive Fine-tuning Platform with WandB Integration
By
–
• Integrating experiment tracking tools like Weights & Biases (WandB)
• Implementing evaluation engines to test model performance against benchmarks MonsterAPIs provides interactive GUI and set of APIs to launch an fine-tuning job on custom datasets in your niche use-cases. -
Tele-FLM-1T: Progressive Training and Depth Growth Techniques
By
–
Here are the juicy lessons from the 1T model Tele-FLM-1T: – Trained progressively in 3 stages: 52B -> 102B -> 1T parameters on ~2T tokens – Depth growth technique: selects layers to duplicate based on their input-output distance metrics, prioritizing middle layers with smaller
-
DeepMind Builds on LeanDojo for AI-Powered Theorem Proving
By
–
I am thrilled to see @GoogleDeepMind build on our work in several instances to strengthen contributions to AI+Science and Math: 1. More than a year ago, we released the first open-source framework, https://
leandojo.org, using Lean+LLM for theorem proving and an AI Lean -
Patterns for Building LLM-based Systems and Products
By
–
Patterns for Building LLM-based Systems & Products https://
bit.ly/45CdmrF
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Learning Orthogonalized Matrices vs Computing Refusal Directions
By
–
I'd say it's different because you learn the orthogonalized matrix with OFT while you compute (you don't learn) your refusal direction here