Convert from TinyLlama/TinyLlama-1.1B-Chat-v1.0 and 4 bits quantized.

Require onnxruntime>=0.17.0

Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for BricksDisplay/TinyLlama-1.1B-Chat-v1.0-q4

Quantized
(109)
this model

Collection including BricksDisplay/TinyLlama-1.1B-Chat-v1.0-q4