We're back up and running with temporary lower rate limits. We apologize to all impacted & will follow up with a post-mortem of what happened and how we'll improve. In the meantime, our status page is here: https://
status.huggingface.co. Thanks all for your support and understanding!
OPEN SOURCE
-
Hugging Face Restores Service with Temporary Rate Limits
By
–
-
LoRAX Open Source Framework Reaches 1000 Stars
By
–
LoRAX, our #opensource framework for cost efficiently serving many #finetuned LLMs on as single GPU, recently joined the 1k club! Check out #LoRA Land to see it in action: https://
pbase.ai/3SXxeAL Download #LoRAX and give it a star if you like it: https://
pbase.ai/49vp89y -
Cerebras AI Day: PyTorch Library and Hardware Innovation
By
–
Our February Newsletter is here! Learn more about the following: Cerebras AI Day and the Go Big or Go Home Party Our new PyTorch library for sparse training Recognition for being the most published AI semiconductor startup Accessing our systems through
-
Bulgarian Developer Makes LLMs Run on CPU with llama.cpp
By
–
2022:
– oh nooo!!! you can't run language models on cpu! you need an expensive nvidia GPU and special CUDA kernels and–
– *one bulgarian alpha chad sits down and writes some c++ code to run LLMs on cpu* – code works fine (don't need a GPU), becomes llama.cpp 2023:
– oh noo!! -
Self-corrective coding assistant with LangGraph and AlphaCodium
By
–
Building a self-corrective coding assistant from scratch with LangGraph Code generation / analysis is one of the most important LLM applications. @itamar_mar and team recently released AlphaCodium, which showed that code generation can be improved by using a flow paradigm to
-
Meta Llama 2 Prompt Engineering Short Course Launch
By
–
New short course: Prompt Engineering with Llama 2, built in collaboration with Meta @AIatMeta, and taught by @asangani7! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you… pic.twitter.com/VVCkl93yzU
— Andrew Ng (@AndrewYNg) 28 février 2024New short course: Prompt Engineering with Llama 2, built in collaboration with Meta @AIatMeta
, and taught by @asangani7
! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you -
Essential Mathematics for Machine Learning: GitHub Repository Guide
By
–
Probability, Statistics, Linear Algebra and Calculus. Checkout the Github Repo → http://
github.com/afshinea/stanf
ord-cs-229-machine-learning
… -
Open-Weight Models Development and Microsoft Reselling Agreement Clarification
By
–
Clarifying a couple of things since we’re reading creative interpretations of our latest announcements:
– We’re still committed to leading open-weight models! We ask for a little patience, 1.5k H100s only got us that far.
– We have a reselling agreement with Microsoft, that we’re -
Langchain-Elasticsearch Integration for Hybrid Retrieval Strategies
By
–
langchain-elasticsearch integration package Use @elastic
’s text and vector search strategies through the new langchain-elasticsearch package. @elastic has been at the forefront of search for years, and the integration package exposes advanced hybrid retrieval strategies