Mistral Small 3: An Excellent 24B-Parameter Wide-Shallow LLM

"Thinking" LLMs with Simple Fine-tuning and Budget Forcing

GRPO: Train LLMs with DeepSeek-R1's Reinforcement Learning Method

Estimating Memory Usage for LLMs During Inference (V2)

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