GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Foodoo1
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
Foodoo1
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
| Field | Qwen3-14B base | + this LoRA |
|---|---|---|
| fraud_risk (4-way, reasoning) | 64.0% | 95.0% |
| block_account (boolean) | 77.0% | 100% |
| language (4-way) | 100% | 100% |
| sentiment (3-way) | 100% | 100% |
| Overall (800 decisions) | 85.2% | 98.8% |
Mean latency: ~234 ms per case (all 4 fields in one broadcast pass, RTX 3090, 4-bit).
All remaining errors are LOW→ELEVATED (conservative direction); zero high-risk cases judged low.
The prompt must match the parallel-constrained format used in training:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-14B", quantization_config=BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16), device_map="auto")model = PeftModel.from_pretrained(base, "Foodoo1/Qwen3-14B-RLCD-Decision-LoRA")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B") catalog = ''' "fraud_risk": Fraud risk tier of this transaction. Choose one of: LOW, ELEVATED, SUSPICIOUS, CRITICAL. "block_account": Whether the account should be blocked immediately'''context = "New device login from abroad, wiring $49,500 offshore, 0 prior transfers." # One prompt per field; decision = argmax over candidate first tokens at the last positionprompt = (f"<|im_start|>system\nClassify JSON attributes:\n{catalog}<|im_end|>\n" f"<|im_start|>user\n{context}<|im_end|>\n" f'<|im_start|>assistant\n{{\n "fraud_risk": "')ids = tok(prompt, return_tensors="pt").to(model.device)logits = model(**ids).logits[0, -1]cands = {c: tok.encode(c, add_special_tokens=False)[0] for c in ["LOW", "ELEVATED", "SUSPICIOUS", "CRITICAL"]}print(max(cands, key=lambda c: logits[cands[c]].item())) # CRITICALFor the full parallel engine (one prefill + KV broadcast for all fields at once), see the harshatheg/Qwen-2.5-1B-RLCD inference code this was evaluated with.
Demonstration/research adapter for structured decision decoding. The fraud-triage schema and data are synthetic; do not use for real financial decisions without domain-specific training and validation.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-14B", quantization_config=BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16), device_map="auto")model = PeftModel.from_pretrained(base, "Foodoo1/Qwen3-14B-RLCD-Decision-LoRA")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B") catalog = ''' "fraud_risk": Fraud risk tier of this transaction. Choose one of: LOW, ELEVATED, SUSPICIOUS, CRITICAL. "block_account": Whether the account should be blocked immediately'''context = "New device login from abroad, wiring $49,500 offshore, 0 prior transfers." # One prompt per field; decision = argmax over candidate first tokens at the last positionprompt = (f"<|im_start|>system\nClassify JSON attributes:\n{catalog}<|im_end|>\n" f"<|im_start|>user\n{context}<|im_end|>\n" f'<|im_start|>assistant\n{{\n "fraud_risk": "')ids = tok(prompt, return_tensors="pt").to(model.device)logits = model(**ids).logits[0, -1]cands = {c: tok.encode(c, add_special_tokens=False)[0] for c in ["LOW", "ELEVATED", "SUSPICIOUS", "CRITICAL"]}print(max(cands, key=lambda c: logits[cands[c]].item())) # CRITICAL