cmsptcp/PLLuM-12B-instruct-FP8-Dynamic

The Model cmsptcp/PLLuM-12B-instruct-FP8-Dynamic was converted to FP8 format from CYFRAGOVPL/PLLuM-12B-instruct using vllm-project/llm-compressor version v0.6.0.

Downloads last month
14
Safetensors
Model size
12B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for cmsptcp/PLLuM-12B-instruct-FP8-Dynamic

Quantized
(5)
this model