Edit model card

Model Card for Model ID

Uses

from transformers import AutoTokenizer, AutoModel  
import torch
model = AutoModel.from_pretrained('princepride/MiniCPM-V-2_6-VPM', trust_remote_code=True,
attn_implementation='flash_attention_2', torch_dtype=torch.bfloat16)
model = model.eval().cuda()  
Downloads last month
5
Safetensors
Model size
418M params
Tensor type
BF16
·
Inference API
Inference API (serverless) does not yet support model repos that contain custom code.