LLMS

–

31 August 2023 1h50

yes, fair, but don't we call this simply "more training"? I dunno, is this really "finetuning"?

Self-supervised Learning and Autoregressive Next-word Prediction Clarification

By

–

31 August 2023 1h43

Self-supervised = autoregressive, next-word prediction like in pretraining? That's what I had in mind with "like pretraining" but in a shorter way to make it fit into the 260 character limit

Defining and Categorizing LLM Fine-tuning Approaches

By

–

31 August 2023 1h37

How do we define and categorize LLM "finetuning" these days? There's 1) Supervised finetuning: to 1a) train an encoder-LLM for classification or 1b) train a decoder-LLM to generate a specific response text. [1/2]

Three types of fine-tuning approaches for language models

By

–

31 August 2023 1h37

[2/2] 2) Instruction finetuning: usually RLHF to generate a specific response. (But can also refer to 1b depending on the technique) 3) Long-context finetuning: like pretraining but w longer contexts (as per Code Llama paper)?

→ View original post on X — @groqinc

Groq Day: AI Acceleration and LLM Inference Solutions

By

@groqinc

–

31 August 2023 1h00

Join us at #GroqDay to understand why now is the moment that matters for AI acceleration of LLMs and how Groq inference solutions provide customer advantages. Register at http://
groq.link/groqday5

→ View original post on X — @aiatmeta

AI Models Benefit from Open Approach Innovation Safety

By

@aiatmeta

–

31 August 2023 0h54

We believe that AI models benefit from an open approach, both in terms of innovation and safety. Releasing models like Code Llama means the entire community can evaluate their capabilities, identify issues & fix vulnerabilities.