GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dwidlee
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
dwidlee
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
staged_v1, option caps ≤8).action_v2 legal-only options (Connect4 drop≤3 + win_now; alerts retained).docs/NOTE_ACTION_V2_QWEN_POSTMORTEM.md.bash
pip install -e ".[dev]" # from the systemone-lite reposystemone-lite --model dwidlee/systemone-lite-0.5b --port 8000python
from systemone_lite import SystemOneClient, choice, noul, score client = SystemOneClient(model="dwidlee/systemone-lite-0.5b")response = client.system_one( state="My card was charged twice.", questions={ "needs_review": noul("Does this need a human agent?"), "route": choice( "Route to a team", {"billing": "charges", "technical": "bugs", "other": None}, ), "urgency": score("Urgency", ["low", "medium", "high"]), },)print(response.answers["route"].choice)Alias-shuffle held-out on Hub test + public JevBench. Not an official
leaderboard submission. n=800 SE ≈ ±1.8%p; n=231 SE ≈ ±3%p — treat small deltas
as noise.
Phase2 held-out (test, n=4700) | 61.6% |
| First-800 protocol (n=800) | 63.9% |
| JevBench public (231 tasks, T=1.0) | 50.7% acc · ECE 0.245 · p50 13.1 ms |
| Short payloads | ~10–30 ms typical (consumer GPU, in-process) |
Uniform-random on the JevBench set is ~32% (many 4–5-way items), not 50%.
Per-gym on full test (weak → strong): game2048 34.6% · sokoban 38.2% · chess 42.0% ·
gridworld 45.6% · connect4 47.0% · CA 50.5% · debate/word ~87% · cloze 89% ·
alloc/ticket ≥98%.
Reports in the GitHub repo:
benchmarks/phase2_heldout__action_v2_qwen.jsonbenchmarks/jevbench_action_v2_qwen.jsonbenchmarks/latency_vs_ar.json (latency methodology; older run)confidence formula.test for held-out eval — never score on train.pip install -e ".[dev]" # from the systemone-lite reposystemone-lite --model dwidlee/systemone-lite-0.5b --port 8000from systemone_lite import SystemOneClient, choice, noul, score client = SystemOneClient(model="dwidlee/systemone-lite-0.5b")response = client.system_one( state="My card was charged twice.", questions={ "needs_review": noul("Does this need a human agent?"), "route": choice( "Route to a team", {"billing": "charges", "technical": "bugs", "other": None}, ), "urgency": score("Urgency", ["low", "medium", "high"]), },)print(response.answers["route"].choice)