shadowlilac
/

lilax-UE-awq

4-bit precision

Model card Files Files and versions Community

shadowlilac commited on Aug 12

Commit

75641ca

•

1 Parent(s): 6d3407b

Update README.md

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

	@@ -1 +1,7 @@
1	- 1b ~~llm based on qwen 2 specifically made for low latency interactions on vrchat~~

+# shadowlilac/limax-UE-awq
+Low-latency Large Language Model (LLM) optimized for fast response times.
+Key Features:
+* Speed: Designed for minimal latency.
+* Quantized: Utilizes AWQ (Adaptive Weight Quantization) for efficiency.
+License: All rights reserved. Contact for commercial use inquiries. Only use for non-commercial personal use cases/studying