Jamba is in the trainer right now. If all goes well, I'll open-source a chat version tonight.
CODE
-
Fine-tune and Serve Open-Source LLMs Efficiently
By
–
Have you ever had these thoughts: Open-source models can't outperform #GPT4 Fine-tuning LLMs is hard Fine-tuned models are costly to serve Well, they're all wrong. See how easy it is to #efficiently fine-tune and serve #LLMs with predibase:
-
Flow Engineering with CodiumAI and LangChain LangGraph Webinar
By
–
Flow Engineering with CodiumAI & LangChain/LangGraph New Webinar Alert: https://
us06web.zoom.us/webinar/regist
er/WN_fVikSl9eQv68b3ZUdQgwzA#/registration
… "Flow Engineering" is a term that has been gaining in popularity recently. The first time it was mentioned as term was in @CodiumAI paper on AlphaCodium, where they used flow -
Finally Paying Down Your Tech Debt
By
–
that feeling when you get to finally get to pay down your tech debt
-
AI21 Labs Thanks Tri Dao for Mamba Extension and Jamba
By
–
Thanks @tri_dao
! We enjoyed the opportunity to extend and build on top of Mamba. The Jamba white paper is coming soon and has some ablations we will share on this subject. -
Snorkel Flow: 96% Recall Model in Three Days Zero Labels
By
–
From zero labeled data to a 96% recall, production-ready model in three days? It may sound impossible, but not with Snorkel Flow.
— Snorkel AI (@SnorkelAI) 28 mars 2024
Snorkel AI's Gabe Smith and Matt Casey recently talked through this impressive case.
Full video here: https://t.co/vGuMawe7LE pic.twitter.com/9FCtJclzBuFrom zero labeled data to a 96% recall, production-ready model in three days? It may sound impossible, but not with Snorkel Flow. Snorkel AI's Gabe Smith and Matt Casey recently talked through this impressive case. Full video here: https://
youtu.be/l4kmQZ50_WQ -
GPTs and Fine-tuning: Understanding AI Model Customization
By
–
Gotcha, thanks Yeah, I know about GPTs – I wrote one of those tutorials myself! https://
simonwillison.net/2023/Nov/15/gp
ts/
… I think of fine-tuning as this kind of thing https://
openai.com/blog/gpt-3-5-t
urbo-fine-tuning-and-api-updates
… -
80k Models Trained with AutoTrain on Hugging Face Hub
By
–
So, you like numbers? Here's a number for you! More than 80k models on Hugging Face Hub have been trained using AutoTrain And probably tens of thousands of other models which are not on the hub since AutoTrain now allows local training Try it now!
-
DS 101 Course Outline: Machine Learning Modeling Theory and Practice
By
–
𝗗𝗦 𝟭𝟬𝟭 𝗖𝗼𝘂𝗿𝘀𝗲 𝗢𝘂𝘁𝗹𝗶𝗻𝗲: https://
aiplus.odsc.com/courses/ds-101
-machine-learning-modelling-in-theory-practice
…
—————————————
Module 1: -Training Overview and Data Science Preliminaries
-Introduction to Modeling Concepts
-Supervised vs. Unsupervised Modeling Module 2: -Insights Discovery and Generalization
-Supervised -
RAG Multi-Representation Indexing Techniques For Document Processing
By
–
RAG From Scratch: Multi-Representation Indexing Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the 12th video in our series and focuses on some useful tricks for indexing full documents. Problem: Many RAG