GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
eorgantzoglou
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
eorgantzoglou
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Evaluated on the 300-message gold set against human labels — the gold set was fully excluded from training:
| Metric | Value |
|---|---|
| Intent accuracy (10 classes) | 73.0% |
| Intent macro-F1 | 0.645 |
| Urgency accuracy (3 levels) | 80.0% |
| Valid JSON output | 300/300 |
The zero-shot base model classifies essentially everything as
general_question — the classification ability comes from these adapters.
Errors concentrate in rare classes (special_assistance: F1 0.29 from only
121 training examples); frequent classes do well (praise 0.91, delay 0.83,
lost luggage 0.80).
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerBASE = "Qwen/Qwen2.5-0.5B-Instruct"ADAPTER = "eorgantzoglou/qwen2.5-0.5b-airline-triage-lora"SYSTEM_PROMPT = ("You are a triage assistant for an airline's customer support. ""Classify the customer tweet. Respond with json only, in exactly this format: "'{"intent": "...", "urgency": "...", "abusive": true/false}. '"intent must be one of: delay_disruption, checkin_boarding_issue, ""flight_cancellation_rebooking, lost_luggage, special_assistance, ""general_complaint, general_question, praise_feedback, spam_irrelevant, ""other_unclear. urgency must be one of: high, medium, low.")tokenizer = AutoTokenizer.from_pretrained(BASE)model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.float32), ADAPTER).merge_and_unload()messages = [{"role": "system", "content": SYSTEM_PROMPT},{"role": "user", "content": "my bags are lost and nobody at the desk is helping"},]inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True),return_tensors="pt",)out = model.generate(**inputs, max_new_tokens=60, do_sample=False,pad_token_id=tokenizer.eos_token_id)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))# {"intent": "lost_luggage", "urgency": "high", "abusive": false}
The system prompt must match the one used in training (above) — the model was fine-tuned with it and expects it verbatim.
special_assistance, spam_irrelevant) have low F1 due to
class imbalance.