Some of the interesting usecases of PEFT are: 1. Stable Diffusion Dreambooth training.
2. Finetuning the `bigscience/T0_3B` model which has around 3 Billion Parameters. Checkout them here: https://
github.com/huggingface/pe
ft#use-cases
… 3/5
CODE
-
Interesting Use Cases of PEFT Parameter Efficient Fine-Tuning
By
–
-
PEFT: Fine-tuning Large Models on Low-End Hardware
By
–
But fine-tuning large models on low-end hardware is a real challenge PEFT solves this by fine-tuning a small number of model parameters while freezing most parameters of the pre-trained LLMs. This reduces the computational and storage costs 2/5 https://
github.com/huggingface/pe
ft
… -
Fine-tuning: Faster Model Adaptation for Specific Tasks
By
–
In simple words fine-tuning is taking a pre-trained machine learning model and adjusting it for a specific task Fine-tuning is much faster than training a model from scratch and also reduces the amount of data, compute required for training and lot of other benefits 1/5
-
PEFT: Fine-tune Large Language Models on Low-Resource Hardware
By
–
Large Language models are expensive to fine-tune and it's really difficult to train them on local hardware. Introducing PEFT ("Parameter-Efficient Fine-Tuning") from Hugging Face that lets you fine-tune Billion Parameter Models on Low-Resource Hardware. A Thread
-
What Could Replace APIs as a Fundamental Technology?
By
–
what will displace APIs? thats a pretty fundamental assumption I don't see changing but am open to ideas
-
GitHub Copilot’s Success: 65% Lifetime Retention Rate in Internal Trials
By
–
Watching @natfriedman tell the story of hammering out the @GitHub Copilot UX with @alexgraveley’s tiny team
— swyx 🐣 (@swyx) 15 février 2023
They knew it was going to be a success when, in internal trials, the lifetime retention rate was >65% 🤯
(at the @heyjasperai conf) pic.twitter.com/bIgvixQfNaWatching @natfriedman tell the story of hammering out the @GitHub Copilot UX with @alexgraveley
’s tiny team They knew it was going to be a success when, in internal trials, the lifetime retention rate was >65% (at the @heyjasperai conf) -
GPT-Based Synthetic Tabular Data Generation Library
By
–
Cool new #GPT-based approach to synthetic tabular data generation. It shows great results compared to the excellent SDV library. Library: https://
github.com/avsolatorio/re
altabformer
… -
LangChain Knowledge Graph Index Structure Exploration
By
–
An AWESOME blogpost by @FanLi_RnD covering the graph index structure we added yesterday https://
apex974.com/articles/explo
re-langchain-support-for-knowledge-graph
… Including some great suggestions for future directions -
LangChain Adds Built-in Tracing Support Docker Image
By
–
great question! yes – we have built in tracing, including support for a locally run docker image https://
langchain.readthedocs.io/en/latest/trac
ing.html
… -
LangChain Integration with BERTopic Now Available
By
–
Really excited to see LangChain integrated with BERTopic! Thanks @MaartenGr https://
maartengr.github.io/BERTopic/getti
ng_started/representation/representation.html#langchain
…