LLM for Coding Benchmarks and Datasets
LiveCodeBench, SWEBench, Aider Polyglot, BBH, HumanEval, MBPP, Common Crawl (Time Span, Dataset Size, Data Format, LLM Testing Capability)
Aug 14, 20251 min read11
Command Palette
Search for a command to run...
#llm
Articles tagged with #llm
How to change a base model to a reasoning model?
Turning a base model into a reasoning model is essentially a post-training + data problem
Aug 14, 20252 min read4
Beyond Pre-training: The Power of RLHF in LLM Alignment
If LLM is compared to a person, then the early training is like general education, and the later training is like vocational training.
Aug 13, 20252 min read21
Key RAG implementation strategies and patterns
Basic RAG Patterns Naive RAG Simple retrieve-then-generate pipeline Direct semantic search → context injection → LLM generation Works well for straightforward Q&A over documents Advanced RAG Pre-retrieval query optimization (query rewriting, expan...
Jul 11, 20252 min read3
Frontier LLM Models for Coding Tasks: Complete Comparison 2025
Comprehensive analysis of the most advanced coding-focused LLM models: Architecture, Context Window, Cost, Performance & Practical Coding Capabilities
Jun 5, 202519 min read61
Optimize Your AI Models: A Deep Dive into LoRA Techniques
Imagine that you have a pre-trained model which works well on task A. Now you get some similar tasks called task B, C, D. How to fine-tune your base model for those new tasks? Can we just update partial of the parameters for each task and run those t...
May 30, 20253 min read3