GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
usejul
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
usejul
Model Tree
openbmb/MiniCPM5-2B
Input Modalities
Output Modalities
Supported Functionality
Choice and Noul better than the vector reading
of the same weights, and Score worse (it rarely picks an end of the scale). decision.json now says so
("routing": {"types": ["score"]}) and jul reads Score with the vector reading it fits on these weights.
This needs a jul with type routing (merged in main, next release); an older jul reads Score with the
pointer head.The previous versions stay available: revision="v1.1" and revision="v1.0".
julbash
jul models add jul-decision-minicpm5-2b --repo usejul/jul-decision-minicpm5-2b --backend torchjul ask choice "Which team should handle this ticket?" -o billing -o shipping -o access \ --state "I was charged twice for order 4411" --model jul-decision-minicpm5-2bpython
from jul import TypeSafeClient, Choice, Noul, Score client = TypeSafeClient(model="jul-decision-minicpm5-2b")answer = client.system_one( state={"subject": "Charged twice", "body": "I see two charges for order #4411."}, questions={"team": Choice(instructions="Which team should handle this ticket?", criteria={"billing": "Payments and refunds", "shipping": "Delivery problems", "access": "Login and account access"}), "angry": Noul(instructions="Is the customer angry?"), "priority": Score(instructions="How urgent is this ticket?", criteria=["low", "normal", "high"])})jul models add also fits the vector reading that Score (and questions with very many options) go to. jul
needs no code specific to this model: the input format, the readout, the pointer head, its temperature and the
routing are in decision.json, next to the weights.
jev-bench: 300 hand-written questions (5 domains: sentiment, finance, support, agent routing, moderation; 100 per type), no 8-gram shared with the training data (one six-word command, "Add milk to my shopping list.", appears in both under other questions), one question per call, PyTorch on an NVIDIA A10G.
| all | Choice | Noul | Score | p50 | |
|---|---|---|---|---|---|
| MiniCPM5-2B, untrained (jul vectors) | 0.630 | 0.75 | 0.66 | 0.48 | 142 ms |
| minicpm5-2b-decision v1.1 | 0.637 | 0.82 | 0.66 | 0.43 | 85 ms |
| jul-decision-minicpm5-2b v2 |
95% intervals are about ±9 points per type (n = 100).
LoRA r=16 on every attention and MLP projection plus a pointer head (dim 256), on Kev's architecture and
training code (Kev, Jared Palmer, Apache-2.0): learning rate 5e-5, batch 8,
one epoch, options reshuffled on every pass, "none of the above" pairs. Base: openbmb/MiniCPM5-2B at
12a3808a.
Apache-2.0, like the base model and Kev's code.
| 0.87 |
| 0.76 |
| 0.41 |
| 85 ms |