Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
2
13
trevon
trevon
Follow
0 followers
·
14 following
https://trevon.dev
trevonistrevon
trvon
AI & ML interests
Computer Networks, Malware, Cryptocurrencies, Artificial Intelligence
Recent Activity
upvoted
an
article
2 days ago
Open-source DeepResearch – Freeing our search agents
reacted
to
singhsidhukuldeep
's
post
with 👀
3 days ago
Excited to share groundbreaking research in Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG)! Researchers from the University of Science and Technology of China have developed FRAG - a novel flexible modular framework that revolutionizes how Large Language Models (LLMs) reason with knowledge graphs. What makes FRAG special? It intelligently adapts retrieval strategies based on query complexity without requiring expensive KG fine-tuning. The framework uses a reasoning-aware module to classify queries as simple or complex, then applies tailored retrieval pipelines. Under the hood: - For simple queries: Uses breadth-first search and ranking to efficiently find relevant paths - For complex queries: Employs shortest path algorithms to minimize computational overhead - Features a preprocessing-retrieval-postprocessing pipeline with flexible components - Leverages traditional algorithms like PersonalizedPageRank for subgraph extraction - Implements edge and path ranking models for precise information filtering The results are impressive - FRAG achieves state-of-the-art performance while maintaining high efficiency and low resource consumption. On benchmark datasets like WebQSP and CWQ, it outperforms existing approaches by significant margins. Most importantly, FRAG maintains flexibility and modularity while improving retrieval quality - no expensive LLM fine-tuning required! This makes it highly practical for real-world applications. This work represents a major step forward in making LLMs more reliable and capable of complex reasoning tasks. Looking forward to seeing how this technology evolves!
liked
a model
6 days ago
tencent/Hunyuan3D-2
View all activity
Organizations
trevon
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
6 days ago
tencent/Hunyuan3D-2
Image-to-3D
•
Updated
4 days ago
•
41k
•
804
liked
a model
8 days ago
qresearch/DeepSeek-R1-Distill-Llama-70B-SAE-l48
Updated
9 days ago
•
10
liked
3 models
9 days ago
Qwen/QwQ-32B-Preview
Text Generation
•
Updated
26 days ago
•
210k
•
•
1.61k
bartowski/deepseek-r1-qwen-2.5-32B-ablated-GGUF
Text Generation
•
Updated
14 days ago
•
122k
•
56
mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit
Updated
14 days ago
•
83
•
2
liked
2 models
10 days ago
BlackBeenie/DeepSeek-R1-Distill-Qwen-32B-Q4_K_M-GGUF
Updated
11 days ago
•
166
•
2
bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF
Text Generation
•
Updated
16 days ago
•
2.25M
•
161
liked
a model
5 months ago
google/gemma-2-2b
Text Generation
•
Updated
Aug 7, 2024
•
238k
•
492
liked
a model
over 1 year ago
codellama/CodeLlama-34b-hf
Text Generation
•
Updated
Apr 12, 2024
•
8.1k
•
168
liked
a Space
over 1 year ago
Running
243
243
BLOOMChat
💬
Generate chat responses with a language model
liked
a model
over 1 year ago
bigcode/starcoder
Text Generation
•
Updated
Oct 8, 2024
•
19k
•
•
2.85k
liked
2 models
almost 2 years ago
tloen/alpaca-lora-7b
Updated
Apr 4, 2023
•
442
bigscience/bloom
Text Generation
•
Updated
Jul 28, 2023
•
2.14M
•
4.83k