divish/M-Prometheus-3B-FP8-Dynamic

This model was converted to FP8_DYNAMIC format from Unbabel/M-Prometheus-3B using llm-compressor via the space. Refer to the original model card for more details on the model.

Downloads last month
2
Safetensors
Model size
3.4B params
Tensor type
FP16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for divish/M-Prometheus-3B-FP8-Dynamic

Base model

Qwen/Qwen2.5-3B
Quantized
(3)
this model