Hugging Face's logo
Rishabh Bhardwaj's picture
6 10 46

Rishabh Bhardwaj

RishabhBhardwaj
megoyaw3's profile picture 21world's profile picture MrOvkill's profile picture
·

AI & ML interests

None yet

Recent Activity

authored a paper about 1 month ago
MSTS: A Multimodal Safety Test Suite for Vision-Language Models
liked a Space 3 months ago
chiayewken/multimodal-longdoc-qwen2-vl
upvoted a paper 4 months ago
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
View all activity

Organizations

Deep Cognition and Language Research (DeCLaRe) Lab's profile picture Sabkuch Align Karo's profile picture Walled AI's profile picture

RishabhBhardwaj's activity

reacted to their post with 👍 8 months ago
view post
Post
2134
Excited to announce the release of the community version of our guardrails: WalledGuard-C!

Feel free to use it—compared to Meta’s guardrails, it offers superior performance, being 4x faster. Most importantly, it's free for nearly any use!

Link: walledai/walledguard-c

#AISafety
  • 1 reply
·
posted an update 8 months ago
view post
Post
2134
Excited to announce the release of the community version of our guardrails: WalledGuard-C!

Feel free to use it—compared to Meta’s guardrails, it offers superior performance, being 4x faster. Most importantly, it's free for nearly any use!

Link: walledai/walledguard-c

#AISafety
  • 1 reply
·
reacted to their post with 🤯 8 months ago
view post
Post
2461
🎉 We are thrilled to share our work on model merging. We proposed a new approach, Della-merging, which combines expert models from various domains into a single, versatile model. Della employs a magnitude-based sampling approach to eliminate redundant delta parameters, reducing interference when merging homologous models (those fine-tuned from the same backbone).

Della outperforms existing homologous model merging techniques such as DARE and TIES. Across three expert models (LM, Math, Code) and their corresponding benchmark datasets (AlpacaEval, GSM8K, MBPP), Della achieves an improvement of 3.6 points over TIES and 1.2 points over DARE.

Paper: DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling (2406.11617)
Github: https://github.com/declare-lab/della

@soujanyaporia @Tej3
  • 3 replies
·
posted an update 8 months ago
view post
Post
2461
🎉 We are thrilled to share our work on model merging. We proposed a new approach, Della-merging, which combines expert models from various domains into a single, versatile model. Della employs a magnitude-based sampling approach to eliminate redundant delta parameters, reducing interference when merging homologous models (those fine-tuned from the same backbone).

Della outperforms existing homologous model merging techniques such as DARE and TIES. Across three expert models (LM, Math, Code) and their corresponding benchmark datasets (AlpacaEval, GSM8K, MBPP), Della achieves an improvement of 3.6 points over TIES and 1.2 points over DARE.

Paper: DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling (2406.11617)
Github: https://github.com/declare-lab/della

@soujanyaporia @Tej3
  • 3 replies
·