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.
LLMS
-
Smaller Open-Source LLMs Can Outperform Larger Commercial Models
By
–
-
Combining LLM self-improvement and inferred consensus
By
–
Fantastic work — imagine combining this with “LLMs Can Self-Improve”! Btw, I suggested LLM-inferred consensus in a tweet last year — AFAIK I thought of it from reading Xuezhi Wang et al. but there may be earlier examples. Case study in “Ideas are cheap; verification is hard.”
-
70B LLMs Performance Compared to GPT-4 in Benchmarks
By
–
So far all these benchmarks are in mandarin. In English it’s still behind GPT4. Still: insane how good 70b LLMs compared to 175b GPT4 is!
-
best_of persists for gpt-3.5-turbo-instruct in Completion API
By
–
best_of still exists in the API for gpt-3.5-turbo-instruct, which will be the only model using the Completion API (which also returns top-5 logprobs) once all legacy completion models are shut off on Jan 4, 2024.
-
A Decade of AI Innovation: Meta’s Transformative Contributions
By
–
10 crazy years — pytorch, detectron, segment-anything, llama, faiss, wav2vec, biggraph, fasttext, the Cake below the cherry, and so much more.
Can't say we didn't change AI and to an extent the world. -
PyTorch LLM Inference Optimization Beats Industry Standards
By
–
using simple pytorch code and advanced features, you get LLM Inference speeds that beat most LLM Inference engines out there. Checkout this great post and work from @cHHillee
-
New Template Redacts Information Before LLM Processing
By
–
Check out this new template that redacts information before processing it with the LLM!
-
Deconstructing RAG: Popular Concepts and Implementation Guide
By
–
Deconstructing RAG Given the importance of RAG and the fast pace of development, we've grouped popular RAG concepts into a few categories and created guides for each one. The this new blog post, we summarize these categories / guides and highlight some questions to ask
-
ChatGPT Transforms Lives as AI Innovation Accelerates
By
–
ChatGPT changed my life and the lives of so many others, excited to see what the next year has in store : )
