EzAudio Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer discuss: https://
huggingface.co/papers/2409.10
819
… demo: https://
huggingface.co/spaces/OpenSou
nd/EzAudio
… Latent diffusion models have shown promising results in text-to-audio (T2A) generation tasks, yet previous models have encountered
OPEN SOURCE
-
EzAudio: Efficient Diffusion Transformer for Text-to-Audio Generation
By
–
-
Together Llama Turbo Demo Now Available on Hugging Face
By
–
demo up on @huggingface
: https://
huggingface.co/spaces/akhaliq
/together-llama-turbo
… -
Llama Model Shows Strong Growth and Increasing Cloud Adoption
By
–
We recently shared an update on the growth of the Llama. Tl;dr: downloads are growing fast, our major cloud partners are seeing rapidly increasing usage of Llama on their platforms and we're seeing great adoption across industries! Read the full update https://
go.fb.me/d01004 -
E2B Code Interpreter: Secure Sandbox for AI-Generated Code Execution
By
–
2/5
— FlowiseAI (@FlowiseAI) 17 septembre 2024
Code Interpreter by @e2b_dev
E2B is an open-source secure sandboxes for AI-generated code execution.
Together with function calling, generated code from LLM can be executed such as plotting graphs, working with pandas dataframe, and displaying the output back to users! pic.twitter.com/ChwbRpkI0m2/5 Code Interpreter by @e2b_dev E2B is an open-source secure sandboxes for AI-generated code execution. Together with function calling, generated code from LLM can be executed such as plotting graphs, working with pandas dataframe, and displaying the output back to users!
-
Flowise Releases Python and Node SDK with OpenAI-Compatible Streaming
By
–
We're excited to introduce Flowise Python and Node SDK!
— FlowiseAI (@FlowiseAI) 17 septembre 2024
🐍pip install flowise
📦npm install flowise-sdk
Streaming is a big part of UX design for LLM apps. With the new SDK, it works exactly the same as the de-facto standard of OpenAI Streaming.
This means we can now easily… pic.twitter.com/aXGiG59Qc4We're excited to introduce Flowise Python and Node SDK! pip install flowise
npm install flowise-sdk Streaming is a big part of UX design for LLM apps. With the new SDK, it works exactly the same as the de-facto standard of OpenAI Streaming. This means we can now easily -
SambaNova Llama 405B faster alternative to OpenAI o1
By
–
Tired of slow thinking with OpenAI o1? Try our demo using the fastest Llama 405B on SambaNova Cloud built by @KyleLiang5
. Try it here: -
PyTorch Async Tensor Parallelism Now Publicly Available
By
–
While async Tensor Parallelism is common among the elite private codebases, the PyTorch team put together a public, accessible and readable one. pretty cool work from @foofoobuggy @cHHillee @lessw2020 @lc_whr tianyu and @wanchao_ Read more here: https://
discuss.pytorch.org/t/distributed-
w-torchtitan-introducing-async-tensor-parallelism-in-pytorch/209487
… -
Own Your Models: Data Privacy and Open-Source LLM Solutions
By
–
If the answer is yes to any of these questions… Do you want to stop sharing #data with commercial LLM providers? Do you want to own your models and weights? Do you want to increase the #throughput / #accuracy of small open-source models? .. then catch the replay of
-
Cute Llama 405B Deployment With Adorable Emotes
By
–
Those emotes might make this the cutest Llama 405B deployment yet.
-
Scale and CAIS Launch Humanity’s Last Exam LLM Benchmark
By
–
As LLMs get smarter, evals need to get harder.
OpenAI’s o1 has already maxed out most major benchmarks. Scale is partnering with CAIS to launch Humanity’s Last Exam: the toughest open-source benchmark for LLMs. We're putting up $500K in prizes for the best questions. (read on)