Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond This survey paper provides a comprehensive and practical guide on working with LLMs for various settings(in-context learning & fine-tuning). I like how it approach LLMs usage in lens of models, data, and
GENERATIVE AI
-
Open Source AI Democratizes Economic Gains for Startups
By
–
This is my 5-minute testimony before the US Congress!
— clem 🤗 (@ClementDelangue) 26 juin 2023
Open science and open source AI distribute economic gains by enabling hundreds of thousands of small companies and startups to build with AI. It fosters innovation, and fair competition between all.
Thanks to ethical… pic.twitter.com/a30RMV2oZWThis is my 5-minute testimony before the US Congress! Open science and open source AI distribute economic gains by enabling hundreds of thousands of small companies and startups to build with AI. It fosters innovation, and fair competition between all. Thanks to ethical
-
Free Generative AI Conference on LLMs and AI Agents July 11
By
–
Free Generative AI Conference on LLMs and AI Agents! July 11. We'll discuss building custom LLMs, simple AI agents, and the future of generative AI. You can register now: https://
eventbrite.com/e/stateofthear
t-free-generative-ai-conference-on-llms-and-ai-agents-tickets-641826449187
…. -
AI Revolutionizing the Working World at Collision 2026
By
–
.
@aidangomezzz
, Cohere's CEO & Co-founder, and @StephenMarche
, novelist and columnist, will be Centre Stage at @CollisionHQ in Toronto. Join them on Thursday, June 29, from 4:30 – 4:50 pm EDT to discuss how AI is revolutionizing the working world. -
HuggingChat Python API: Free Open Source ChatGPT Alternative
By
–
HuggingChat is a free and open source alternative to commercial chat offerings such as ChatGPT. The unofficial Python API gives you immediate access, without signup, for free. HuggingChat Python API: Your No-Cost Alternative – KDnuggets https://
bit.ly/3NgE3u7 -
Collaborative LLM Project with Falcon and LLaMA Teams
By
–
This was a really cool project with @clefourrier @nathanhabib1011 @osanseviero and a lot of help from @slippylolo from the Falcon team and the amazing LLaMA team, in particular Xavier Martinet, Aurélien Rodriguez and Sharan Narang!
-
Open Standardized Benchmarks Essential for AI Model Evaluation
By
–
24/ That's why open, standardized, reproducible benchmarks such as the EleutherAI Harness https://
github.com/EleutherAI/lm-
evaluation-harness/
… or Stanford HELM https://
github.com/stanford-crfm/
helm/
… are invaluable to the community. Without them comparing results across models/papers would be impossible, stifling research! -
Probability-based sequence generation normalization in language models
By
–
19/ In this case, we use probabilities again but this time we compute the probability of generating the full answer sequence, not just the letter: we sum the log of the probabilities and compute a normalization by dividing by the number of tokens to not penalize longer sequences.
-
HELM Implementation: Model Evaluation via Token Probabilities
By
–
16/ HELM: Now let's take a look at the HELM implementation. The few-shot prompt is similar but the way the model is evaluated is quite different: we use the next token probabilities from the model to select a text generation and we compare it to the text of the expected answer
-
Two main ways to evaluate model outputs
By
–
11/ In summary, we have two main ways to evaluate a model outputs:
1. Get the probabilities that some tokens are continuations of the prompt => compare these probabilities together
2. Get the text generation from the model => compare these text generations to possible choices