Local Agentic AI with smolagents and Qwen2.5 Coder

Deploy Your Fine-Tuned LoRA Adapters with Ollama

Fast and Memory-Efficient Text-to-SQL with Qwen2.5 Coder 32B Instruct on Your GPU

Schedule-Free Optimizer: Does It Work for LLMs?

Fine-Tuning Llama 3.3 70B with a Single GPU

Quantize and Run Llama 3.3 70B Instruct on Your GPU

LLM Alignment: Searching for Optimal ORPO Hyperparameters

The Recipe for Extremely Accurate and Cheap Quantization of 70B+ LLMs

DPO Full Training vs. LoRA: How Good is LoRA for DPO Training?

Torch Compile: 2x Faster Llama 3.2 with Low Effort

LLM as a Judge: Evaluate Your LLMs with Another LLM

Llama 3.2 Embeddings: Training and Evaluation with LLM2Vec