GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
FluidInference
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
FluidInference
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
joint_schema_model.py is Cloudflare's unchanged Clef module (record encoding, head, ClefModel).
python
import json, sys, torchfrom huggingface_hub import snapshot_downloadfrom safetensors.torch import load_filefrom transformers import AutoModelForCausalLM, AutoTokenizer path = snapshot_download("FluidInference/clef-text-0.6b")sys.path.insert(0, path)from joint_schema_model import ClefModel, JointSchemaHead, collate_records, encode_record tokenizer = AutoTokenizer.from_pretrained(path)backbone = AutoModelForCausalLM.from_pretrained(path, dtype=torch.float32)head = JointSchemaHead(**json.loads(open(f"{path}/joint_head_config.json").read()))head.load_state_dict(load_file(f"{path}/joint_head.safetensors"))model = ClefModel(backbone, head).eval() record = {"state": "Our checkout is down and customers can't pay.", "questions": {"team": {"type": "choice", "instructions": "Which team should handle this?", "criteria": {"billing": "Payments", "engineering": "Bugs or outages"}}, "urgency": {"type": "score", "criteria": ["Low", "Normal", "High", "Critical"]}}}encoded = encode_record(tokenizer, record)with torch.inference_mode(): logits = model(collate_records([encoded], tokenizer.pad_token_id, torch.device("cpu")))[0]for question, question_logits in zip(encoded.questions, logits): print(question.question_id, dict(zip(question.option_ids, question_logits.softmax(-1).tolist())))| Task | this model | clef-flash 9B |
|---|---|---|
| DBpedia-14 | 99.7 | 100.0 |
| AG News | 90.7 | 92.0 |
| SST-2 | 90.0 | 94.0 |
| BANKING77 | 86.4 | 94.5 |
| TweetEval offensive | 85.0 | 82.3 |
| Yelp stars | 69.0 | 70.7 |
| Emotion | 68.0 | 58.0 |
| BoolQ | 82.3 | 90.7 |
| MNLI | 72.3 | 84.3 |
| ARC-Easy | 80.0 | 100.0 |
| CommonsenseQA | 65.0 | 94.3 |
| ARC-Challenge | 60.7 | 97.3 |
| all (5,124 q) | 79.1 | 88.2 |
Training: 24,208 records from 12 public datasets (train splits) labelled by clef-flash, KL (T = 2) + 0.3 gold CE, LoRA r64 + full head, 2 epochs on an M5 Pro.
Apache-2.0. joint_schema_model.py and LICENSE are Cloudflare's (Apache-2.0). Teacher
Cloudflare/clef-flash; base Qwen/Qwen3-0.6B.
By Fluid Inference.
import json, sys, torchfrom huggingface_hub import snapshot_downloadfrom safetensors.torch import load_filefrom transformers import AutoModelForCausalLM, AutoTokenizer path = snapshot_download("FluidInference/clef-text-0.6b")sys.path.insert(0, path)from joint_schema_model import ClefModel, JointSchemaHead, collate_records, encode_record tokenizer = AutoTokenizer.from_pretrained(path)backbone = AutoModelForCausalLM.from_pretrained(path, dtype=torch.float32)head = JointSchemaHead(**json.loads(open(f"{path}/joint_head_config.json").read()))head.load_state_dict(load_file(f"{path}/joint_head.safetensors"))model = ClefModel(backbone, head).eval() record = {"state": "Our checkout is down and customers can't pay.", "questions": {"team": {"type": "choice", "instructions": "Which team should handle this?", "criteria": {"billing": "Payments", "engineering": "Bugs or outages"}}, "urgency": {"type": "score", "criteria": ["Low", "Normal", "High", "Critical"]}}}encoded = encode_record(tokenizer, record)with torch.inference_mode(): logits = model(collate_records([encoded], tokenizer.pad_token_id, torch.device("cpu")))[0]for question, question_logits in zip(encoded.questions, logits): print(question.question_id, dict(zip(question.option_ids, question_logits.softmax(-1).tolist())))