cmsptcp/Llama-PLLuM-8B-instruct-FP8-Dynamic

The Model cmsptcp/Llama-PLLuM-8B-instruct-FP8-Dynamic was converted to FP8 format from CYFRAGOVPL/Llama-PLLuM-8B-instruct using vllm-project/llm-compressor version 0.7.2.dev10+g5b3ddff7.

Downloads last month
20
Safetensors
Model size
8.03B 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/Llama-PLLuM-8B-instruct-FP8-Dynamic

Quantized
(5)
this model