GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mjusdda
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mjusdda
Model Tree
unsloth/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
Full evaluation used 50 target samples and 15 general-regression samples. Generation was greedy on a Colab NVIDIA T4.
| Run | Target | Regression | JSON format | Latency (ms/sample) |
|---|---|---|---|---|
| Base + naive prompt | 0.000 | 0.7578 | 0.000 | 3370.5 |
| Base + optimized prompt | 0.765 | 0.7578 | 1.000 | 1066.3 |
| This LoRA adapter | 0.970 | 0.6778 | 1.000 | 1511.4 |
The adapter improves target score by +0.205 over the optimized-prompt baseline, but
regression drops by -0.080, beyond the allowed tolerance of -0.020. The formal
verdict is therefore FAILED. This is an honest experimental result, not a claim that
the adapter is production-ready. See submission/REPORT.md and
the machine-readable files under results/.
unsloth/Qwen3.5-4Br=16, alpha=321e-4python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "unsloth/Qwen3.5-4B"adapter_id = "mjusdda/lab21-2A202601343-qwen35-triage-vi" tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)base = AutoModelForCausalLM.from_pretrained( base_id, trust_remote_code=True, dtype=torch.float16, device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id) ticket = "Shop ơi, đơn bàn phím cơ của tôi giao chậm quá. Nhờ kiểm tra gấp."messages = [ {"role": "system", "content": "Phân loại ticket sau."}, {"role": "user", "content": ticket},]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device)with torch.no_grad(): output = model.generate(**inputs, max_new_tokens=160, do_sample=False)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))This adapter is intended for education, reproducibility, and experiments with Vietnamese ticket triage. Expected closed-vocabulary values are:
intent: doi_tra, van_chuyen, hoan_tien, san_pham_loi, hoi_thong_tinurgency: cao, trung_binh, thapsentiment: tieu_cuc, trung_tinh, tich_cucproduct: product name copied from the ticketurgency=trung_binh when the correct value was thap.submission/REPORT.mdresults/verdict.json,
results/runs.csv, and results/autopsy.jsonThe adapter follows the Apache-2.0 license declared by the base model. The accompanying lab code repository is separately licensed under MIT.
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "unsloth/Qwen3.5-4B"adapter_id = "mjusdda/lab21-2A202601343-qwen35-triage-vi" tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)base = AutoModelForCausalLM.from_pretrained( base_id, trust_remote_code=True, dtype=torch.float16, device_map="auto",)model = PeftModel.from_pretrained(base, adapter_id) ticket = "Shop ơi, đơn bàn phím cơ của tôi giao chậm quá. Nhờ kiểm tra gấp."messages = [ {"role": "system", "content": "Phân loại ticket sau."}, {"role": "user", "content": ticket},]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device)with torch.no_grad(): output = model.generate(**inputs, max_new_tokens=160, do_sample=False)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))