Stanford CS25: V4 I Aligning Open Language Models

  Рет қаралды 17,758

Stanford Online

Stanford Online

Ай бұрын

April 18, 2024
Speaker: Nathan Lambert, Allen Institute for AI (AI2)
Aligning Open Language Models
Since the emergence of ChatGPT there has been an explosion of methods and models attempting to make open language models easier to use. This talk retells the major chapters in the evolution of open chat, instruct, and aligned models, covering the most important techniques, datasets, and models. Alpaca, QLoRA, DPO, PPO, and everything in between will be covered. The talk will conclude with predictions and expectations for the future of aligning open language models. Slides posted here: docs.google.com/presentation/...
All the models in the figures are in this HuggingFace collection: huggingface.co/collections/na...
About the speaker:
Nathan Lambert is a Research Scientist at the Allen Institute for AI focusing on RLHF and the author of Interconnects.ai. Previously, he helped build an RLHF research team at HuggingFace. He received his PhD from the University of California, Berkeley working at the intersection of machine learning and robotics. He was advised by Professor Kristofer Pister in the Berkeley Autonomous Microsystems Lab and Roberto Calandra at Meta AI Research.
More about the course can be found here: web.stanford.edu/class/cs25/
View the entire CS25 Transformers United playlist: • Stanford CS25 - Transf...

Пікірлер: 9
@SebastianRaschka
@SebastianRaschka Ай бұрын
This talk and the slides are gold! Love the whirlwind tour of the BC (Before ChatGPT) and AD (After Deployment of ChatGPT). How fast time went by ... I barely remember Vicuna, and it was just a year ago :D
@nafikhan13-4-23
@nafikhan13-4-23 Ай бұрын
I love 💓💓💓💓Stanford Online💓💓💓💓
@mahirturjo7509
@mahirturjo7509 Ай бұрын
❤❤❤❤❤❤
@user-wr4yl7tx3w
@user-wr4yl7tx3w Ай бұрын
Shouldn’t there be a different KZbin channel for AI from Stanford.
@raul36
@raul36 24 күн бұрын
If AI is aligned then it is not AGI.
@TheAlphaWavePodcast
@TheAlphaWavePodcast 9 күн бұрын
Stanford has thirst traps? Who knew?
@CannabinatedFantasy
@CannabinatedFantasy Ай бұрын
omg his forehead
@TheAlphaWavePodcast
@TheAlphaWavePodcast 9 күн бұрын
I have a PhD in law and I have gone through the arduous process of establishing a very viable patent, trademark and copyright case that I am sure can help Nathan trademark his forehead so we can sue the creators of the film Megamind for billions. Please Nathan, contact me.
Stanford CS25: V4 I Demystifying Mixtral of Experts
1:04:32
Stanford Online
Рет қаралды 4,8 М.
Stanford CS25: V3 I Retrieval Augmented Language Models
1:19:27
Stanford Online
Рет қаралды 141 М.
Её Старший Брат Настоящий Джентельмен ❤️
00:18
Глеб Рандалайнен
Рет қаралды 8 МЛН
Smart Sigma Kid #funny #sigma #comedy
00:19
CRAZY GREAPA
Рет қаралды 11 МЛН
Data + AI Summit Keynote Day 1 - Full
2:52:20
Databricks
Рет қаралды 13 М.
Wolfram Physics Project: Relations to Category Theory
3:54:12
Wolfram
Рет қаралды 444 М.
Mind Your Language: Thought, Metaphor and Imagination
1:51:58
World Science Festival
Рет қаралды 849 М.
This is why Deep Learning is really weird.
2:06:38
Machine Learning Street Talk
Рет қаралды 352 М.
Think Fast, Talk Smart: Communication Techniques
58:20
Stanford Graduate School of Business
Рет қаралды 38 МЛН
God-Tier Developer Roadmap
16:42
Fireship
Рет қаралды 6 МЛН
Stanford CS25: V4 I Jason Wei & Hyung Won Chung of OpenAI
1:17:07
Stanford Online
Рет қаралды 145 М.
AI and Quantum Computing: Glimpsing the Near Future
1:25:33
World Science Festival
Рет қаралды 304 М.