Stories by danielhanchen

Python 3.11 is 1.25x faster than 3.10

Fixing Gradient Accumulation

Unit Economics of LLM APIs

LoRA Learns Less and Forgets Less Updated

VLLM automatic prefix / prompt caching

Higher Temperatures and Min_p Sampling

Show HN: Open-source fine-tuning in a Colab notebook

Sahm rule signals start of recession

Low Level Technicals of LLMs [video]

Gemma-2 2B beats GPT3.5 on Chatbot Arena

HuggingChat – Chat UI for Llama 3.1 405B

Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth

Yield Curve and Predicted GDP Growth

Cloudflare DNS + Malware Blocking

SIMD at Insomniac Games: How We Do the Shuffle

Some Machine Learning Notes

Show HN: Finetune Llama-3.1 2x faster in a Colab

Show HN: Mistral NeMo finetuning fits in Colab

TextGrad – Backpropagation through text feedback

1 2