GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
JumperV
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
JumperV
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
| Test | Base model | Diapason | Change (points) |
|---|---|---|---|
| MusicTheoryBench: knowledge (269 Qs, chance 25%) | 59.1% | 58.7% | -0.4 |
| MusicTheoryBench: reasoning (98 Qs, chance 25%) | 33.7% | 34.7% | +1.0 |
| MusicTheoryBench: all (367 Qs) | 52.3% | 52.3% | +0.0 |
| Theory drills: exact answer (held out) | 15.1% | 89.4% | +74.3 |
| Opera / theory questions: score (held out) | 44.4% | 43.8% | -0.6 |
| Opera / theory questions: fully correct | 29.2% | 17.2% | -12.0 |
| Opera / theory questions: wrong | 40.4% | 29.6% | -10.8 |
QLoRA (4-bit NF4 base, bf16 compute), LoRA r=16, alpha=32, dropout 0.05 on q/k/v/o/gate/up/down projections; 2 epochs, learning rate 2e-4 with cosine schedule, effective batch size 16, max length 768, loss on answers only. Trained with TRL + PEFT on a single RTX 3060 12 GB.
Use the system prompt below (Diapason was trained with it) and, for calculations, ask for step-by-step working. The results above were measured with the NF4 4-bit setup shown here.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel BASE = "Qwen/Qwen3-4B-Instruct-2507"tok = AutoTokenizer.from_pretrained(BASE)# NF4 4-bit, the setup Diapason was trained with (about 3-4 GB of VRAM).# Note: plain BitsAndBytesConfig(load_in_4bit=True) defaults to FP4, which gives noticeably worse answers.bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16)model = AutoModelForCausalLM.from_pretrained(BASE, quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(model, "JumperV/Diapason") SYSTEM = "You are a knowledgeable tutor in opera and music theory. Answer clearly and accurately."STEPS = '\n\nWork it out briefly step by step, then give the final answer on the last line as "Answer: ...".' def ask(question, calculation=False): msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": question + (STEPS if calculation else "")}] inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**inputs, max_new_tokens=400, do_sample=False) return tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(ask("Spell the German augmented sixth chord in C minor.", calculation=True))print(ask("What is a leitmotif, and which composer is most associated with it?"))Tips:
Answer: ...; read that line.dtype="auto", about 9 GB of VRAM) also works; all reported results used NF4.import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel BASE = "Qwen/Qwen3-4B-Instruct-2507"tok = AutoTokenizer.from_pretrained(BASE)# NF4 4-bit, the setup Diapason was trained with (about 3-4 GB of VRAM).# Note: plain BitsAndBytesConfig(load_in_4bit=True) defaults to FP4, which gives noticeably worse answers.bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16)model = AutoModelForCausalLM.from_pretrained(BASE, quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(model, "JumperV/Diapason") SYSTEM = "You are a knowledgeable tutor in opera and music theory. Answer clearly and accurately."STEPS = '\n\nWork it out briefly step by step, then give the final answer on the last line as "Answer: ...".' def ask(question, calculation=False): msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": question + (STEPS if calculation else "")}] inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**inputs, max_new_tokens=400, do_sample=False) return tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(ask("Spell the German augmented sixth chord in C minor.", calculation=True))print(ask("What is a leitmotif, and which composer is most associated with it?"))