Try it out: https://
ui.endpoints.huggingface.co How can we make Inference Endpoints more cost-effective for the ML community? shipped by @_philschmid @LucSGeorges
OPEN SOURCE
-
Hugging Face Makes ML Inference More Cost-Effective
By
–
-
Hugging Face invites community collaboration with git-based platform
By
–
we'd love to have you at @huggingface Let us know if we can help in any way! And it's just git underneath so you wouldn't be locked in any way. cc @_josh_meyer_ @reach_vb
-
GPT Engineer: AI-Powered Code Generation from Natural Language Specifications
By
–
GPT Engineer
— AK (@_akhaliq) 20 juin 2023
github: https://t.co/I3oXZXmvYT
Specify what you want it to build, the AI asks for clarification, and then builds it.
GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based… pic.twitter.com/UvMNw2RgAOGPT Engineer github: https://
github.com/AntonOsika/gpt
-engineer
… Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based -
Adding Function Chains: Extraction, Tagging, Question-Answering
By
–
So that's the general formula for how we're adding `functions` chains So far we've added: – Extraction
– Tagging
– Question-Answering with citations We're EXTREMELY open to contributions here – with this formula should be a pretty easy addition -
Setting Up Model Repositories on Hugging Face Hub
By
–
Happy to help y’all setup your model repos on Hugging Face Hub I think the community will really benefit from this!
-
Full Parameter Fine-tuning for Large Language Models with Limited Resources
By
–
Full Parameter Fine-tuning for Large Language Models with Limited Resources paper page: https://
huggingface.co/papers/2306.09
782
… Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but demand massive GPU resources for training. Lowering the threshold for LLMs -
OpenLLaMA 13B: Open Source LLaMA Reproduction Released
By
–
OpenLLaMA 13B Released model: https://
huggingface.co/openlm-researc
h/open_llama_13b
… present a permissively licensed open source reproduction of Meta AI's LLaMA large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA -
VideoComposer Todo: 8-Second Video Generation Without Watermark
By
–
under todo: https://
github.com/damo-vilab/vid
eocomposer#todo
… "Release pretrained model that can generate 8s videos without watermark." -
VideoComposer: Controllable Motion Video Synthesis Models Released
By
–
VideoComposer: Compositional Video Synthesis
— AK (@_akhaliq) 17 juin 2023
with Motion Controllability models are out!
paper page: https://t.co/jb0kyDGCVH
github: https://t.co/GARo57U90t
The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in… pic.twitter.com/7RFfNJq3TVComposer: Compositional Synthesis
with Motion Controllability models are out! paper page: https://
huggingface.co/papers/2306.02
018
…
github: https://
github.com/damo-vilab/vid
eocomposer
… The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in -
PyTorch Distributed Training and Tensor Sharding with Fabric
By
–
None of these: just PyTorch with distributed training and tensor sharding. Optionally with CPU offloading for really big LLMs. I use Fabric as a convenient wrapper here.