GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Samarth101011
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Samarth101011
Model Tree
HuggingFaceTB/SmolVLM-Instruct
Input Modalities
Output Modalities
Supported Functionality
HuggingFaceTB/SmolVLM-Instructpython
import torchfrom transformers import AutoProcessor, AutoModelForVision2Seqfrom peft import PeftModel base_model_id = "HuggingFaceTB/SmolVLM-Instruct"adapter_id = "Samarth101011/clinixvault-smolvlm-qlora" # 1. Load Base Modelbase_model = AutoModelForVision2Seq.from_pretrained( base_model_id, torch_dtype=torch.float16, device_map="auto") # 2. Attach ClinixVault Fine-Tuned Adaptermodel = PeftModel.from_pretrained(base_model, adapter_id)model.eval()print("ClinixVault model ready for inference.")This model is designed for clinical decision support under licensed clinical supervision. Verified under the ClinixVault Zero-Data-Egress Clinical Verification Framework.