Edit model card

omost-phi-3-mini-128k-8bits is Omost's phi-3-mini model with 128k context length in fp8.

Downloads last month
1,078
Safetensors
Model size
3.82B params
Tensor type
F32
BF16
I8
Inference Examples
Input a message to start chatting with lllyasviel/omost-phi-3-mini-128k-8bits.
Inference API (serverless) has been turned off for this model.