Ready to efficiently #finetune Llama-2-70B on a single A100 #GPU the easy way? Check out our blog to learn how to use #opensource @ludwig_ai and a simple configuration to fine-tune #Llama70B for structured JSON generation and outperform #GPT4! https://
pbase.ai/3NeMsiM
@predibase
-
Fine-tune Llama-2-70B on Single A100 GPU Efficiently
By
–
-
Migrating from OpenAI to Open Source LLMs: Complete Guide
By
–
Most teams start their #LLM journey prototyping with #OpenAI. They quickly realize that they want to migrate to #opensource LLMs—motivated by a desire to reduce costs and own their model IP But how do you make the switch? We've got you covered https://
pbase.ai/3RxDxdF -
Fine-tune LLMs easily with Ludwig AI without expertise
By
–
Can you fine-tune #LLMs without being an expert? Yep, it's possible (hint: open-source @ludwig_ai
) Don't take it from us though. Check out this awesome post from #AI expert and coach, Yogesh Haribhau Kulkarni (PhD). https://
pbase.ai/46Jn3o5 -
101 Guide to Fine-tuning Open-source LLMs
By
–
Here's your 101 Guide to #Fine-tuning Open-source #LLMs thanks to @AnalyticsVidhya and @predibase ML Engineer, @grg_arnav https://
pbase.ai/417L9rA -
7 Essential Things to Know About LLM Fine-Tuning
By
–
ICYMI: We recently hosted an interactive discussion with our #LLM experts on 7 Things You Need to Know About #Finetuning. Here's the session recording: https://
pbase.ai/3sRBVDd. And, if you're interested, try fine-tuning and serving LLMs for free: https://
pbase.ai/3RpF5Hy. -
Smaller Open-Source LLMs Can Outperform Larger Commercial Models
By
–
Hot take: bigger isn't always better. Especially when we're talking about #LLMs. Smaller, faster #opensource LLMs can outperform much larger and more expensive commercial LLMs when #finetuned for a task. Try fine-tuning for free: https://
pbase.ai/40YVJRH. -
Low-code declarative ML: Beyond AutoML hype to practical solutions
By
–
Low-code vs. no-code #ML: what's hype and what really works? New article from @devvret_rishi on why #autoML tools have failed us and how low-code approaches like #DeclarativeML—pioneered by @ludwig_ai
—makes it easy to build powerful custom AI models -
LoRAX v0.2: Sparse SGMV and Tensor Parallel Inference
By
–
Announcing LoRAX v0.2 Sparse SGMV: vectorize LoRA and base model requests in same batch Tensor Parallel SGMV: multi-GPU, multi-LoRA vectorized inference ExLlama v2 kernels for faster GPT-Q (thanks Florian Zimmermeister!)
…and more! https://
pbase.ai/3T2Nemt -
Open-source LLMs: Smaller, faster, cheaper alternatives to commercial models
By
–
Open-source LLMs like #Llama2 are smaller, faster & cheaper than commercial #LLMs like @OpenAI #GPT4 — and best of all, when fine-tuned they can deliver equivalent if not better performance Join our webinar to learn how you can get started #finetuning. https://
pbase.ai/49RLm6a -
Ludwig Reaches 10,000 GitHub Stars – Join Giveaway Competition
By
–
We're excited to announce that Ludwig has reached 10,000 stars on Github Help celebrate by participating in our 10k Giveaway Competition. Share your Ludwig projects (see link below) and our favorites will win a limited edition swag pack https://
pbase.ai/3MXE3jA