Sublime
An inspiration engine for ideas
HOLY SHITT, Microsoft dropped an open-source Multimodal (supports Audio, Vision and Text) Phi 4 - MIT licensed! š„
> Beats Gemini 2.0 Flash, GPT4o, Whisper, SeamlessM4T v2
> Models on Hugging Face hub, integrated with/ Transformers!
Phi-4-Multimodal:
___LINEBREAK... See more
Nice paper for a long read across 114 pages.
"Ultimate Guide to Fine-Tuning LLMs"
Some of the things they cover
š Fine-tuning Pipeline
Outlines a seven-stage process for fine-tuning LLMs, from data preparation to deployment and maint... See more
Lil'Log
lilianweng.github.ioTL;DR
LLMLingua utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
... See more
LLMLingua utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
... See more
microsoft ā¢ GitHub - microsoft/LLMLingua: To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Neuro-Linguistic Programming Explained: Your Definitive Guide to NLP Mastery: (NLP Techniques, Neuroplasticity, Hypnosis, Meditation, Psychotherapy, Communication, Emotional Intelligence, Confidence)
amazon.com
Introducing Neurolinguistic Programming (NLP): A Practical Guide (Introducing...)
amazon.com
