Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
Paper
•
2503.06269
•
Published
Privacy Preserving AI Hackathon (Zama, Hugging Face, Entrepreneur First)
Enterprise
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
ppaihack's activity
Sckathach
authored
a
paper
5 days ago
Post
1656
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2:
An Investigation of FP8 Across Accelerators for LLM Inference (2502.01070)
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
Post
1022
Nice to see day 1 support of Falcon 3 on Gaudi with Optimum Habana!
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
👉 https://www.intel.com/content/www/us/en/developer/articles/technical/intel-ai-solutions-support-falcon-3-fdn-models.html
benkoska
authored
a
paper
3 months ago
Post
1419
Interested in performing inference with an ONNX model?⚡️
The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!
You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!
You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
from optimum.onnxruntime import ORTModelForSequenceClassification
# Load the model from the hub and export it to the ONNX format
model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = ORTModelForSequenceClassification.from_pretrained(model_id, export=True)Check out the whole guide 👉 https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
VaultChem
updated
a
Space
5 months ago
jeremyzacch
updated
a
Space
6 months ago
nizarzerouale
updated
a
Space
6 months ago
Mojmir
updated
a
Space
6 months ago
WenqingZhang
updated
a
Space
6 months ago
TomSmail
updated
a
Space
6 months ago
tagny
updated
a
Space
6 months ago
Sckathach
updated
a
Space
6 months ago
micpst
updated
a
Space
6 months ago
n-schuldt
updated
a
Space
6 months ago
AeternumS
updated
2
Spaces
6 months ago
Nos7
updated
a
Space
6 months ago
lucacolombo97
updated
a
Space
6 months ago
gregoiregllt
updated
a
Space
6 months ago