3/ Extremely low memory footprint. LoRA trainable parameters are only 0.2% of total amount of model parameters.
@predibase
-
How LoRA is Transforming LLM Fine-tuning Techniques
By
–
1/ Curious how #LoRA is changing fine-tuning? Read our latest blog post to learn more! #llm #finetune
-
Fine-tuning Index: Compare Open-Source LLMs Across Tasks
By
–
Curious which fine-tuned #opensource LLM performs best for your task? 📊
— Predibase by Rubrik (@predibase) 5 juin 2024
We ran 100s of #finetuning jobs and shared our findings in our Fine-tuning Index. The Task #Leaderboard allows you to compare 10+ open-source LLMs across 30 tasks.
Check it out: https://t.co/ZMT6XcHc5H pic.twitter.com/Hel9GZL4saCurious which fine-tuned #opensource LLM performs best for your task? We ran 100s of #finetuning jobs and shared our findings in our Fine-tuning Index. The Task #Leaderboard allows you to compare 10+ open-source LLMs across 30 tasks. Check it out: https://
pbase.ai/459drE5 -
Train Custom LLM Beating GPT-4 Free Workshop
By
–
What if… you could train an LLM to beat GPT-4 for your use case? and, that LLM was open-source and <1% the size of GPT-4? and, you could do it for free? If that sounds appealing, then don't miss our virtual workshop – free compute included! https://
pbase.ai/3x5lepL -
Predibase at Snowflake Data Cloud DevDay: Train Custom LLMs
By
–
If your in San Francisco, don't miss the @SnowflakeDB #DataCloudDevDay this Thursday! Find us at booth 2126J to learn how to train your own task-specific #LLM that rivals #GPT4—directly on top of your #Snowflake Data Cloud! Save your spot: https://
pbase.ai/459dxeQ -
Predibase Joins LLM Conf with Free Credits and Expert Speakers
By
–
We're super excited to be a part of this amazing #LLM Conf from the genius minds of @HamelHusain + @dan_s_becker alongside so many other thought leaders in AI. Today is your last chance to register and get all of the free credit goodness! Not to mention you will learn a ton!
-
Fine-tuning LLMs for 2x Faster Inference with Speculative Decoding
By
–
Fine-tuning #LLMs isn't just for customization You can also #finetune LLMs to increase throughput using speculative decoding Check out the replay of our recent tech talk to learn how we fine-tuned an LLM using to increase inference by 2x https://
pbase.ai/4bV6rNc. -
Free Meetup: Building LLM Serving Platforms at Scale with NVIDIA
By
–
Bay Area Friends: Join us tomorrow at Orchestrating #GenAI Apps Meetup with NVIDIA and NetApp. We'll be discussing what it takes to build an #LLM serving platform at scale. Best of all it's free to attend, save your spot:
-
LoRA Fine-tuning and Medusa Boost LLM Throughput Performance
By
–
Throughput or performance? Pick both with LoRA fine-tuning & Medusa! Did you miss our webinar yesterday on speculative decoding? Check it out! We cover: Why are LLMs slow? How does fine-tuning with Medusa 2x throughput? How does Predibase help? https://
pbase.ai/3yuNeDM -
Zephyr Leads Fine-Tuning Performance Leaderboard
By
–
Thanks for the shoutout. Here’s the link to the full leaderboard: https://
predibase.com/fine-tuning-in
dex
…. Great seeing Zephyr continue to perform so strongly!