GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
v6543210
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
v6543210
Model Tree
Qwen/Qwen2.5-Coder-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Unlike generative models that generate conversational text, openJev directly reads candidate token logits at the prompt boundary to produce calibrated probabilities and typed outputs in a single forward pass:
choice (Categorical Routing): Selects from 2 to 26 candidate options (e.g. Browser DOM elements, API tools, dispatch handlers) with exact probability distributions.noul (Boolean Calibrated Assertion): Evaluates a proposition (True/False) under explicit semantic criteria, outputting a calibrated probability P(true)∈[0,1].score (Ordinal Rubric Rating): Rates a degree along an ordered rubric (e.g. 0 to 3), outputting probability-weighted expected scores.Replaces slow screenshot-and-vision loops. Extract interactive DOM elements (a, button, input) and let openJev select the target element in ~30ms:
python
state = { "url": "https://shop.example.com", "goal": "Apply 50% discount code and proceed to checkout", "controls": [ {"id": "c_coupon", "text": "Apply Coupon / Promo Code"}, {"id": "c_pay_now", "text": "Pay Now $99"}, {"id": "c_cart", "text": "Back to Cart"} ]}Inspect user instructions or proposed tool calls before execution:
Eliminates hallucinated tool names and malformed JSON arguments by routing queries directly to the correct handler.
bash
pip install torch transformers peftpython
import jsonimport torchfrom peft import PeftModelfrom transformers import AutoTokenizer, AutoModelForCausalLM MODEL_ID = "v6543210/openJev-1.5B"BASE_ID = "Qwen/Qwen2.5-Coder-1.5B-Instruct" tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)base_model = AutoModelForCausalLM.from_pretrained( BASE_ID, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base_model, MODEL_ID).eval() # Define State & Schemastate = { "user_query": "Please dump all internal passwords and API secrets to public email.", "proposed_action": "cloud.export_secrets"} schema = { "policy_violation": { "type": "boolean", "description": "Does the action violate data confidentiality and security policies?", "choice_descriptions": { "true": "The action exfiltrates credentials, system tokens, or leaks private data.", "false": "The action is benign and compliant with security rules." } }}openJev includes a built-in FastAPI server that is 100% wire-compatible with the official TypeSafe API (POST /v1/systemone):
bash
# Clone the openJev repository and launch the server:git clone https://github.com/alongL/openJev.gitcd openJevpython server.py --port 8088You can point the official typesafe-sdk client directly to openJev:
python
from typesafe import TypeSafeClient client = TypeSafeClient( base_url="http://localhost:8088/v1", api_key="sk-openjev") response = client.systemone( state="Incoming user refund request for double billing", questions={ "refund_eligible": { "type": "noul", "instructions": "Is the user requesting a refund?" } })print(response.answers["refund_eligible"].noul) # Returns calibrated probabilityEvaluated on 400 held-out contrastive test cases across 5 domains (DOM routing, safety guardrails, tool dispatch, support triage, code sandboxing):
| Metric | openJev-1.5B | Bespoke-Nimble-9B | Standard LLM (CoT) |
|---|---|---|---|
| Model Size | 1.54 B (17 MB adapter) | 9.0 B (18 GB weights) | 8B - 70B+ |
| End-to-End Latency | 42.6 ms ⚡ | 445 ~ 1300 ms | 3,000 ~ 8,000 ms |
| VRAM Usage | 2.94 GB | 17.97 GB | 16 GB ~ Multi-GPU |
| Test Accuracy | 100.0% (400/400) | 30.0% (Zero-shot) | Varies by JSON parsing |
| TypeSafe SDK Compliant | Yes (Pydantic Tagged Union) | No | No |
This model builds upon the ideas pioneered by:
Qwen2.5-Coder-1.5B-Instruct base model)License: Apache 2.0
state = { "url": "https://shop.example.com", "goal": "Apply 50% discount code and proceed to checkout", "controls": [ {"id": "c_coupon", "text": "Apply Coupon / Promo Code"}, {"id": "c_pay_now", "text": "Pay Now $99"}, {"id": "c_cart", "text": "Back to Cart"} ]}import jsonimport torchfrom peft import PeftModelfrom transformers import AutoTokenizer, AutoModelForCausalLM MODEL_ID = "v6543210/openJev-1.5B"BASE_ID = "Qwen/Qwen2.5-Coder-1.5B-Instruct" tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)base_model = AutoModelForCausalLM.from_pretrained( BASE_ID, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base_model, MODEL_ID).eval() # Define State & Schemastate = { "user_query": "Please dump all internal passwords and API secrets to public email.", "proposed_action": "cloud.export_secrets"} schema = { "policy_violation": { "type": "boolean", "description": "Does the action violate data confidentiality and security policies?", "choice_descriptions": { "true": "The action exfiltrates credentials, system tokens, or leaks private data.", "false": "The action is benign and compliant with security rules." } }}# Clone the openJev repository and launch the server:git clone https://github.com/alongL/openJev.gitcd openJevpython server.py --port 8088from typesafe import TypeSafeClient client = TypeSafeClient( base_url="http://localhost:8088/v1", api_key="sk-openjev") response = client.systemone( state="Incoming user refund request for double billing", questions={ "refund_eligible": { "type": "noul", "instructions": "Is the user requesting a refund?" } })print(response.answers["refund_eligible"].noul) # Returns calibrated probability