16 21

blank reg

blankreg

·

AI & ML interests

None yet

Recent Activity

reacted to singhsidhukuldeep's post with 🚀 12 days ago

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

new activity 22 days ago

microsoft/phi-4:GGUF quants

liked a model about 1 month ago

mradermacher/HuatuoGPT-o1-8B-GGUF

View all activity

Organizations

None yet

blankreg's activity

New activity in microsoft/phi-4 22 days ago

GGUF quants

#15 opened 25 days ago by

New activity in mradermacher/model_requests about 1 month ago

HuatuoGPT-o1 models

#523 opened about 1 month ago by

New activity in mradermacher/model_requests about 2 months ago

Llama-3.1-8B-UltraMedical

#499 opened about 2 months ago by

New activity in bartowski/Qwen2.5-Coder-7B-Instruct-GGUF about 2 months ago

Update?

#4 opened about 2 months ago by

New activity in mradermacher/model_requests 5 months ago

https://huggingface.co./johnsnowlabs/JSL-Med-Phi-3.5-Mini-v3

#290 opened 5 months ago by

New activity in mradermacher/model_requests 6 months ago

https://huggingface.co./johnsnowlabs/JSL-MedLlama-3-8B-v17-8bits

#233 opened 6 months ago by

New activity in mradermacher/JSL-MedMX-7X-GGUF 8 months ago

JSL-MedPhi2

#1 opened 9 months ago by

New activity in johnsnowlabs/JSL-MedPhi2-2.7B 9 months ago

GGUF quants?

#1 opened 9 months ago by

New activity in bartowski/Meta-Llama-3-8B-Instruct-GGUF 9 months ago

You think you could re-quant with the regex fix?

#3 opened 9 months ago by

New activity in mradermacher/model_requests 10 months ago

https://huggingface.co./FreedomIntelligence/Apollo-7B

#31 opened 10 months ago by

New activity in FreedomIntelligence/Apollo-7B 10 months ago

Quantized versions please?

#1 opened 11 months ago by

New activity in MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF 10 months ago

stop token fix?

#7 opened 10 months ago by

New activity in CohereForAI/c4ai-command-r-v01-4bit 10 months ago

GGUF format for LM-Studio etc.

#1 opened 11 months ago by

New activity in MaziyarPanahi/medicine-chat-GGUF 10 months ago

text-generation-webui?

#2 opened 10 months ago by

text-generation-webui?

#2 opened 10 months ago by