You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Access to ProKope-421M-8K weights is provided for academic evaluation, benchmarking, and commercial licensing inquiries. Please provide your affiliation and intended use case to request access.
Log in or Sign Up to review the conditions and access this model content.
ProKope-421M-8K
Introduction
ProKope-421M-8K is a 421M-parameter non-autoregressive classification and scoring model developed by ProKope AI, based on ModernBERT-large with a 8,192-token context window. It evaluates structured state inputs in a single forward pass across three typed decision primitives:
noul: Binary boolean classification ([0, 1]probability).choice: Multi-class categorical routing.score: Ordinal severity and confidence estimation ([0, 1]scalar).
For 1,024-token context workloads, see ProKope-421M.
Evaluation
Evaluated across 400 test cases (2,000 total decisions) on the LocalLLaMA/typed-decisions benchmark:
| Model | Parameters | Context | Overall Accuracy | Decisions Correct | Brier Score |
|---|---|---|---|---|---|
| ProKope-421M-8K | 421M | 8,192 | 71.85% | 1,437 / 2,000 | 0.384 (raw) |
| Featherless Simple Jev | 35B | 8,192 | 71.60% | 1,432 / 2,000 | 0.110 |
| ProKope-421M | 421M | 1,024 | 71.40% | 1,428 / 2,000 | 0.071 (calibrated) |
| prima-ratio | 12B | 8,192 | 70.20% | 1,404 / 2,000 | 0.125 |
| mgoeckel/oscar-1-400m | 400M | 1,024 | 70.00% | 1,400 / 2,000 | 0.062 |
| OpenDecider-small | 4B | 8,192 | 67.10% | 1,342 / 2,000 | 0.117 |
| Bekko System One v0 | 400M | 1,024 | 66.80% | 1,336 / 2,000 | 0.113 |
Domain Breakdown (ProKope-421M-8K: 71.85% / 1,437 / 2,000)
- Invoice Processing: 79.80% (399 / 500)
- Agent-Trace Observability: 73.80% (369 / 500)
- Security Incidents: 69.60% (348 / 500)
- Customer Service Routing: 64.20% (321 / 500)
Decision Primitive Breakdown
noul(Binary Decision): 80.50%choice(Multi-Class Routing): 70.00%score(Ordinal Severity): 66.75%
Model Details
| Property | Value |
|---|---|
| Backbone | ModernBERT-large (28 bidirectional encoder layers, 1,024 hidden size) + 2-layer multi-head decision projection |
| Total Parameters | 421,293,830 (803.57 MB in bfloat16) |
| Context Window | 8,192 tokens (head_max_len: 256 tokens) |
| Throughput | |
| Recommended VRAM | 2 GB+ for bfloat16 / float16 inference |
| Precision | torch.bfloat16 |
| License | CC-BY-NC-4.0 (Commercial licensing available via ProKope AI) |
Quickstart
1. Python Inference (RLAgent)
from rl_agent_api import RLAgent
agent = RLAgent("ProKope-AI/ProKope-421M-8K")
state = (
"Production API Gateway alert: 504 Gateway Timeout spiked to 14.8% over the last 3 minutes. "
"Worker node 4 pod eviction reported due to memory pressure (96.2%)."
)
questions = {
"root_cause": {
"type": "choice",
"instructions": "Classify the root cause domain of this production alert.",
"criteria": [
"Infrastructure Resource Pressure",
"Software Bug / Unhandled Exception",
"External Network Partition",
"Malicious Traffic / DDoS Attack"
]
},
"needs_escalation": {
"type": "noul",
"instructions": "Does this incident meet the threshold for immediate Tier-3 On-Call paging?",
"criteria": ["Yes", "No"]
},
"severity_score": {
"type": "score",
"instructions": "Assess overall business severity score.",
"criteria": ["Low", "Medium", "High", "Critical"]
}
}
results = agent.system_one(state, questions)
for key, ans in results["answers"].items():
print(key, "->", ans)
2. Reproducing the Benchmark Evaluation
python eval_prokope.py
Limitations & Intended Use
- Intended Use: Low-latency structured classification, incident triage, workflow routing, and calibrated probability estimation over bounded decision schemas (
noul,choice,score). - Limitations:
ProKope-421M-8Kis a non-autoregressive encoder-classifier and does not generate free-form text. Inputs exceeding the 8,192-token context window are truncated.
Contact & Citation
- Organization: ProKope AI
- Authors: Alan Canto, Wesley Foreman
- Inquiries & Commercial Licensing: prokope.model@gmail.com
@misc{canto2026prokope421m8k,
author = {Alan Canto and Wesley Foreman},
title = {ProKope-421M-8K: Non-Autoregressive Structured Typed Decision Model},
howpublished = {Hugging Face},
year = {2026},
url = {https://huggingface.co/ProKope-AI/ProKope-421M-8K}
}
- Downloads last month
- -