Model Card for Model ID

Model Details

Model Description

GPTQ-4bit quantization version (disable exllama) of https://huggingface.co/T3LS/stella-mrl-large-zh-v3.5-1792d-1024

Uses

model = AutoModelForSequenceClassification.from_pretrained(
    'T3LS/stella-mrl-large-zh-v3.5-1792d-1024-gptq-4bit',
)
Downloads last month
15
Safetensors
Model size
64.7M params
Tensor type
I32
·
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.