Views
No views yet
TinyLlama/TinyLlama-1.1B-Chat-v1.0 and is converted to the OpenVINO format. This model was obtained via the nncf-quantization space with optimum-intel.optimum-intel installed:pip install optimum[openvino]1from optimum.intel import OVModelForCausalLM
2
3model_id = "dpastushenkov/TinyLlama-1.1B-Chat-v1.0-openvino-8bit"
4model = OVModelForCausalLM.from_pretrained(model_id)