GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Overup
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Overup
Model Tree
unsloth/Llama-3.2-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from unsloth import FastLanguageModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="unsloth/Llama-3.2-3B-Instruct", max_seq_length=1024, load_in_4bit=True,)model.load_adapter("Overup/cc-lead-classifier") prompt = """<|system|>You are a lead qualification assistant for a home services company. Analyze contact form submissions and classify them as VALID_LEAD or SPAM.</s><|user|>Classify this contact form submission: Name: Jane SmithEmail: jane@example.comPhone: 555-0123Message: I need a quote for a custom walk-in closet in my master bedroom.</s><|assistant|>""" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=80)print(tokenizer.decode(outputs[0]))