Seen in Denmark DagsHug = @TheRealDagsHub + @huggingface ?!
@julien_c
-
Open Source Project Corrects Licensing Decision Early
By
–
the reality is that we started working on that project organically without thinking (enough) about how we would like to license it that's what @ClementDelangue says too: we made a licensing mistake and wanted to correct it early rather than wait more and be stuck with it
-
TGI Inference Project Positioning Debate
By
–
don't really agree here:
1/
TGI is/was super early in its history (very few outside contributors, and we discussed with all of them) 2/
it's smaller than other similar inference projects (vllm, …) so unclear it had even "taken the lead" Happy to discuss further though! -
AWS Launches NVIDIA H100 Instances to General Availability
By
–
in case you missed it @awscloud just shipped their nvidia H100 instances as GA yesterday only the 8xH100 flavor is available for now, so it's a bit hefty https://
aws.amazon.com/ec2/instance-t
ypes/p5/
… -
Deploying Dedicated Inference Endpoints for Large-Scale AI
By
–
(For large-scale deployments, you can deploy a dedicated Inference Endpoint)
-
Llama 2 Now Available on Inference API for Free
By
–
Llama 2 just landed in Inference API It is available for free for PRO and Enterprise Hub users (no additional per-token billing) Just start making HTTP calls and use one of the best open LLMs, no infra needed
-
Legal and Machine Learning Intersection Discussion
By
–
some quite good threads of Legal ∩ ML in this Hackernews thread https://
news.ycombinator.com/item?id=368152
55
… -
Llamas Take Over Hugging Face Hub Platform
By
–
ok so llamas have taken control of the @huggingface hub…
-
Model Parameters Now Exposed in API for Safetensors Weights
By
–
> Note that model params were inferred by name For all models that have safetensors weights (i.e. more and more) we expose number of params (and types) in the API and on model pages!
-
Llama 2 70B Now Available on HuggingChat
By
–
Llama 2 (70B) just landed in HuggingChat This is the largest running version of the model from @MetaAI
, running on fast optimized inference on @huggingface infra. Unleash the llamas! Try it out now http://
hf.co/chat