agentica/JSL-MedFalcon-10B-Merged-v2-Slerp-pt-4bit
Updated
•
16
•
2
blank reg
blankreg
·
AI & ML interests
None yet
Recent Activity
new activity
about 11 hours ago
mradermacher/model_requests:can you quantize this?
liked
a model
about 11 hours ago
agentica/JSL-MedFalcon-10B-Merged-v2-Slerp-pt-4bit
liked
a model
4 days ago
microsoft/phi-4-gguf
Organizations
None yet
blankreg's activity
can you quantize this?
1
#649 opened about 11 hours ago
by
blankreg
liked
a
model
about 11 hours ago
liked
a
model
4 days ago
i1 or not?
2
#1 opened 6 days ago
by
blankreg
liked
a
model
6 days ago
reacted to
singhsidhukuldeep's
post with 🚀
19 days ago
Post
2966
Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments.
Key innovations that set MiniRAG apart:
Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval
Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery
Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%
The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.
This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments
The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
Key innovations that set MiniRAG apart:
Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval
Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery
Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%
The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.
This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments
The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
- 1 reply
GGUF quants
2
#15 opened about 1 month ago
by
apepkuss79
liked
3
models
about 1 month ago
HuatuoGPT-o1 models
1
#523 opened about 1 month ago
by
blankreg
liked
2
models
about 2 months ago
Llama-3.1-8B-UltraMedical
3
#499 opened about 2 months ago
by
blankreg
liked
3
models
about 2 months ago
liked
a
model
2 months ago
liked
a
model
5 months ago