GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MaestroYan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MaestroYan
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
python
import json, torchfrom huggingface_hub import hf_hub_downloadfrom peft import PeftModelfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration base, adapter = "Qwen/Qwen3.8-27B", "MaestroYan/JEMM"processor = AutoProcessor.from_pretrained(base)model = Qwen3_5ForConditionalGeneration.from_pretrained(base, dtype=torch.bfloat16, device_map="cuda")model = PeftModel.from_pretrained(model, adapter).eval()config = json.load(open(hf_hub_download(adapter, "decision_config.json")))labels = [chr(65 + i) for i in range(26)] + list("012345")system = "Choose the best available candidate for the question using only the supplied state. Return exactly one candidate label." def decide(state, question, candidates, image=None): flat = lambda s: " ".join(s.split()) options = "\n".join(f"{labels[i]}) {flat(c)}" for i, c in enumerate(candidates)) text = f"State:\n{state.strip()}\n\nQuestion: {flat(question)}\n\nCandidates:\n{options}\n\nAnswer with exactly one candidate label." content = ([{"type": "image"}] if image else []) + [{"type": "text", "text": text}] messages = [{"role": "system", "content": system}, {"role": "user", "content": content}] prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) inputs = processor(text=[prompt], images=[image] if image else None, return_tensors="pt").to(model.device, dtype=torch.bfloat16) with torch.inference_mode(): logits = model(**inputs, logits_to_keep=1).logits[0, -1] ids = [processor.tokenizer.encode(x, add_special_tokens=False)[0] for x in labels[:len(candidates)]] probs = torch.softmax(logits[ids].float() / config["mm_temperature" if image else "temperature"], -1) return dict(zip(candidates, probs.tolist())) decide("User: Will it rain in Paris tomorrow?", "Which tool should handle the request?", ["get_weather: weather forecast for a city", "search_flights: flight search", "No tool applies"])2 to 32 candidates per question. Screenshots are PIL images; training used 1280x800. Treat a top probability below threshold in decision_config.json as undecided. HTTP server: JEMM on GitHub.
Mind2Web, xLAM function-calling-60k (APIGen), xlam-irrelevance, When2Call, Banking77, MASSIVE, Aegis 2.0 (CC-BY-4.0); CLINC150 (CC-BY-3.0); BFCL, glaive-function-calling-v2, ToolACE, hermes-function-calling-v1 (Apache-2.0); Multimodal-Mind2Web (OpenRAIL). No Jev outputs were used.
import json, torchfrom huggingface_hub import hf_hub_downloadfrom peft import PeftModelfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration base, adapter = "Qwen/Qwen3.8-27B", "MaestroYan/JEMM"processor = AutoProcessor.from_pretrained(base)model = Qwen3_5ForConditionalGeneration.from_pretrained(base, dtype=torch.bfloat16, device_map="cuda")model = PeftModel.from_pretrained(model, adapter).eval()config = json.load(open(hf_hub_download(adapter, "decision_config.json")))labels = [chr(65 + i) for i in range(26)] + list("012345")system = "Choose the best available candidate for the question using only the supplied state. Return exactly one candidate label." def decide(state, question, candidates, image=None): flat = lambda s: " ".join(s.split()) options = "\n".join(f"{labels[i]}) {flat(c)}" for i, c in enumerate(candidates)) text = f"State:\n{state.strip()}\n\nQuestion: {flat(question)}\n\nCandidates:\n{options}\n\nAnswer with exactly one candidate label." content = ([{"type": "image"}] if image else []) + [{"type": "text", "text": text}] messages = [{"role": "system", "content": system}, {"role": "user", "content": content}] prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) inputs = processor(text=[prompt], images=[image] if image else None, return_tensors="pt").to(model.device, dtype=torch.bfloat16) with torch.inference_mode(): logits = model(**inputs, logits_to_keep=1).logits[0, -1] ids = [processor.tokenizer.encode(x, add_special_tokens=False)[0] for x in labels[:len(candidates)]] probs = torch.softmax(logits[ids].float() / config["mm_temperature" if image else "temperature"], -1) return dict(zip(candidates, probs.tolist())) decide("User: Will it rain in Paris tomorrow?", "Which tool should handle the request?", ["get_weather: weather forecast for a city", "search_flights: flight search", "No tool applies"])