Benchmarking Language Model Performance on 5th Gen Xeon at GCP
•
5
Intel
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Intel's activity
aahouzi
updated
a
model
7 days ago
aahouzi
published
a
model
7 days ago
PhillipHoward
updated
a
dataset
9 days ago
PhillipHoward
published
a
dataset
9 days ago
ek-id
updated
a
model
11 days ago
n1ck-guo
updated
a
dataset
11 days ago
Adding ONNX file of this model
#4 opened 19 days ago
by
ek-id
n1ck-guo
updated
a
dataset
23 days ago
estellea
authored
3
papers
3 months ago
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Paper
•
2404.01197
•
Published
•
31
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models
Paper
•
2404.03118
•
Published
•
25
FastRM: An efficient and automatic explainability framework for multimodal generative models
Paper
•
2412.01487
•
Published
•
1
daniel-de-leon
posted
an
update
4 months ago
Post
2407
As the rapid adoption of chat bots and QandA models continues, so do the concerns for their reliability and safety. In response to this, many state-of-the-art models are being tuned to act as Safety Guardrails to protect against malicious usage and avoid undesired, harmful output. I published a Hugging Face blog introducing a simple, proof-of-concept, RoBERTa-based LLM that my team and I finetuned to detect toxic prompt inputs into chat-style LLMs. The article explores some of the tradeoffs of fine-tuning larger decoder vs. smaller encoder models and asks the question if "simpler is better" in the arena of toxic prompt detection.
🔗 to blog: https://huggingface.co/blog/daniel-de-leon/toxic-prompt-roberta
🔗 to model: Intel/toxic-prompt-roberta
🔗 to OPEA microservice: https://github.com/opea-project/GenAIComps/tree/main/comps/guardrails/toxicity_detection
A huge thank you to my colleagues that helped contribute: @qgao007 , @mitalipo , @ashahba and Fahim Mohammad
🔗 to blog: https://huggingface.co/blog/daniel-de-leon/toxic-prompt-roberta
🔗 to model: Intel/toxic-prompt-roberta
🔗 to OPEA microservice: https://github.com/opea-project/GenAIComps/tree/main/comps/guardrails/toxicity_detection
A huge thank you to my colleagues that helped contribute: @qgao007 , @mitalipo , @ashahba and Fahim Mohammad
abenmao
authored
a
paper
8 months ago
wenhuanh
authored
a
paper
8 months ago
tybrs
authored
a
paper
11 months ago
shaoyent
authored
a
paper
over 1 year ago
estellea
authored
a
paper
over 1 year ago
qgao007
authored
a
paper
over 1 year ago
guybd
authored
a
paper
over 1 year ago