Categories

5 pages

Llm

Constrained Decoding: How We Actually Get Structure Out of LLMs

Llm Structured-Outputs Constrained-Decoding Vllm

Fine-Tuning a 4B Model Into Your Own Persona, Part 2: Training, Eval, Ship

Llm Sft Fine-Tuning Lora

Fine-Tuning a 4B Model Into Your Own Persona, Part 1: The Data

Llm Sft Fine-Tuning Lora

Costume vs. Character: How $35 of SFT Turned Qwen Into Monty

Llm Sft Fine-Tuning Lora

Small Dog, Small Language Model: Training a Transformer for $5

Llm Transformer Pytorch Hugging-Face