Introducing HELMET
•
22
Intel
company
Verified
AI & ML interests
None defined yet.
Recent Activity
Articles
Intel's activity
bconsolvo
updated
a
Space
1 day ago
PhillipHoward
updated
a
dataset
2 days ago
bconsolvo
published
a
Space
8 days ago
bconsolvo
updated
a
Space
8 days ago
ek-id
updated
a
Space
18 days ago
bconsolvo
published
a
Space
20 days ago
ek-id
published
a
Space
24 days ago
n1ck-guo
updated
a
dataset
26 days ago
yishanwang
authored
a
paper
27 days ago
bconsolvo
updated
a
Space
about 1 month ago
ashahba
updated
a
Space
about 2 months ago
aahouzi
updated
a
model
about 2 months ago
aahouzi
published
a
model
about 2 months ago
PhillipHoward
updated
a
dataset
about 2 months ago
PhillipHoward
published
a
dataset
about 2 months ago
ek-id
updated
a
model
about 2 months ago
Adding ONNX file of this model
#4 opened 2 months ago
by
ek-id
daniel-de-leon
posted
an
update
6 months ago
Post
2417
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
ashahba
authored
a
paper
about 1 year ago
kylemin
authored
a
paper
about 1 year ago