5/ Foundation models are great, but they're just a foundation. For business-critical applications where quality matters, use the full slate of data-centric model improvement techniques!
LLMS
-
DistilBERT Fine-Tuning Achieves 84 F1 With Programmatic Labeling
By
–
4/ For maximum quality, we finished with fine-tuning, using Snorkel Flow to programmatically label data in areas where the model was still underperforming. Our best model (~84 F1) is fine-tuned DistilBERT, a model 10,000x smaller than GPT-4.
-
Fine-tuning and Prompt Engineering Outperform GPT-4 Baseline
By
–
1/ Prompt engineering LLMs is valuable, but used alone leaves many points on the table. See how we combine prompt engineering and fine-tuning to create a specialized model that outperforms prompted GPT-4 by 15 to 34 points on a real-world extraction task! https://
snkl.ai/pro -
Perspectives on Diffusion Models in AI and Machine Learning
By
–
Perspectives on diffusion https://
bit.ly/45nzZjn #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Llama 2 Now Available on IBM watsonx.ai Platform
By
–
We’re excited for even more people to be able to build with Llama 2 on https://t.co/ZEoYo4mPNn! https://t.co/RruqN3rTzC
— AI at Meta (@AIatMeta) 9 août 2023We’re excited for even more people to be able to build with Llama 2 on http://
watsonx.ai! -
Ludwig v0.8: Open-Source Low-Code Framework for LLM Fine-Tuning
By
–
Announcing Ludwig v0.8—the first #opensource low-code framework optimized for building and #finetuning LLMs on your data. New features incl. fine-tuning, integrations w/ Deepspeed, parameter efficient fine-tuning (#LoRA), prompt templating and more!
-
Hugging Face Launches TRL for RLHF Model Training
By
–
TRL Hugging Face Excited to announce that we're doubling down on our efforts to democratize RLHF and reinforcement learning with TRL, new addition to the @huggingface family, developed and led by team member @lvwerra Train your first RLHF model https://
github.com/huggingface/trl -
Claude Instant 1.2 Enhanced Math Coding Reasoning Capabilities
By
–
Claude Instant 1.2 incorporates the strengths of Claude 2 in real-world use cases and shows significant gains in key areas like math, coding, and reasoning. It generates longer, more structured responses and follows formatting instructions better.
-
Claude Instant 1.2 Now Available via Anthropic API
By
–
Developers looking to work with Claude Instant 1.2 can now call our latest model over our API! https://
docs.anthropic.com/claude/referen
ce/selecting-a-model
… -
Claude Instant 1.2 API Launch: Faster, Capable Model
By
–
Introducing our latest version of Claude Instant, version 1.2, available now through our API!
— Anthropic (@AnthropicAI) 9 août 2023
Claude Instant is our faster, lower-priced yet still very capable model, which can handle a range of tasks including dialogue, analysis, summarization, and document comprehension. pic.twitter.com/p9M2d7O9K9Introducing our latest version of Claude Instant, version 1.2, available now through our API! Claude Instant is our faster, lower-priced yet still very capable model, which can handle a range of tasks including dialogue, analysis, summarization, and document comprehension.