Why the generosity? Competition is heating up, with rivals like Google, Anthropic, and open-source models pushing prices down. OpenAI’s response? Make it easier and cheaper for devs to create custom AI.
LLMS
-
OpenAI fine-tuning dashboard: quick start with GPT-4o model
By
–
Developers can get started right away by visiting OpenAI’s fine-tuning dashboard. Just select gpt-4o-2024-08-06 as the base model, and you're good to go. The process is straightforward, but the impact? Huge.
-
OpenAI GPT-4 Customization for Developers: Fine-Tuning Guide
By
–
Breaking: OpenAI just made GPT-4 customizable for developers. Fine-tune the model to meet your exact needs, with no massive dataset required. Here’s how you can get started today. Plus, a special offer you won’t want to miss: ↓
-
LLMs behave like predictive text influenced by chat conditioning
By
–
There’s no dialog before this, to be clear — I didn’t ask it to pretend. LLMs are just like this. Though there’s some some conditioning from the implicit chat syntax (“user:” etc.), to a much greater extent than most widely used LLMs this model really is “just predicting text.”
-
Most models use instruct SFT and RL-based tuning
By
–
Most models that normal people have used in the past year (ChatGPT, Gemini, Claude, etc.) have some form of both instruct SFT and RL-based tuning. But yes I’m using “RLHF” inexactly in my post as a synecdoche for all post-training.
-
Pretraining and conditioning issues in instruct-tuned dialogue models
By
–
There’s conditioning from the dialog syntax that it’s being naively given in the same format that the instruct-tuned version receives. It’s seen these in pre-training, but the association isn’t strong enough apparently to make it act like a chatbot even most of the time.
-
Example contrasting base LLMs and RLHF-tuned models
By
–
I tried to write a prompt to show how base LLMs differ from the RLHF-tuned ones everyone knows, and I think this gives a bit of the flavor. A message from Llama 3.1 405B (base), on whether it’s useful to talk to base LLMs:
-
FocusLLM: Scaling LLM Context Through Parallel Decoding
By
–
FocusLLM Scaling LLM's Context by Parallel Decoding discuss: https://
huggingface.co/papers/2408.11
745
… Empowering LLMs with the ability to utilize useful information from a long context is crucial for many downstream applications. However, achieving long context lengths with the conventional -
Discussion on RLHF vs post-training model comparisons
By
–
You’re not comparing RLHF to no RLHF here, you’re comparing different generations post-RLHF mystery models, likely of different sizes. If you don’t do post-training at all, naive attempts to talk to the model go like this:
-
Benchmarking LLMs: A Comprehensive Guide for Performance Evaluation
By
–
We should do a blog post on this. It could really help benchmark LLMs