Hugging Face's logo

Spaces:
Ahmadzei
/
RAG
Runtime error

App Files Community
RAG / chunked /nltk_chunking /_quantization /chunk_69.txt
Ahmadzei's picture
Ahmadzei
added 3 more tables for large emb model
5fa1a76
raw
history blame contribute delete
114 Bytes
 4-bit quantization compresses a model even further, and it is commonly used with QLoRA to finetune quantized LLMs.