4/6 Fine-Tuning Index shows #OSS #LLMs outperforming GPT-4 on 85% of tested tasks
@predibase
-
Apple’s GenAI Architecture: Small Fine-Tuned Models LoRA
By
–
3/6 #Apple's #GenAI architecture: Small, fine-tuned models with #LoRA adapters
-
Fine-tuned Solar LLM Outperforms GPT-4 on Most Tasks
By
–
2/6 Fine-tuned Solar LLM outperforms #GPT-4 in over 80% of tasks. Try it yourself!
-
Platform Refactoring for Enhanced Robustness and Maintainability
By
–
We’re in the process of refactoring to make it easier to update and more robist. Stay tuned!
-
LoRA: Efficient LLM Fine-tuning Technique for Custom Applications
By
–
Building with #LLMs? Then you owe it to yourself to know about #LoRA. LoRA is an #efficient technique for #finetuning pre-trained LLMs for your use case. It's the same technique employed by @Apple and what we use to train small models that beat #GPT4.
-
Solar LLM: Best Model for Fine-Tuning Performance
By
–
Which LLM is best for fine-tuning? @upstageai
's #SolarLLM! Join our webinar to learn how Solar: Beat #GPT-4 #llama3 #phi3 #zephyr and #mistral Was the #1 LLM in over 50% of tasks Is available exclusively on Predibase for fine-tuning
Register –> https://
pbase.ai/3W1huiL -
Predibase Featured as SLM Leader in CB Insights Enterprise AI Report
By
–
@CBinsights just dropped their new Enterprise #AI Roadmap report and @predibase is on the front cover as a leader in small task-specific models The report talks about the growing trend of small language models (#SLM) and much more. Check it out: https://
cbinsights.com/research/repor
t/enterprise-ai-roadmap/
… -
Small LLMs Fine-tuning with Snowflake Data Cloud Integration
By
–
Small #models that punch above their weight class now connected to all of your #data in the @SnowflakeDB data cloud! Replay from our latest talk on how to easily, and efficiently #finetune small open-source #LLMs that provide big model results! https://
youtube.com/watch?v=szmOLw
ZdWuQ
… -
Apple’s GenAI Strategy: Small Models and LoRA Adapters at Scale
By
–
ICYMI: @Apple recently published their playbook for deploying #GenAI at scale across iOS devices. What's their secret? Small language models (#SLM) + lots of fine-tuned #LoRA adapters. Want to can replicate their approach? Check out our blog: https://
pbase.ai/3KXrIdO -
Tinder’s Production Safety and Trust Systems Using Lorax Technology
By
–
Here’s an upcoming talk from Tinder about their use of Lorax for their production safety and trust systems: https://
ai.engineer/worldsfair/202
4/schedule/ai-frontiers-in-trust-and-safety-combatting-multifaceted-harm-on-tinder-at-scale
….