Modelpublic

noffy/hastejev-5m

sourceHugging Faceapache-2.0updated 5h agoView on Hugging Face

0likes16downloads

Model Card

Haste Jev 5m (Medium)

Role: Finance / KYC workflow branch

Open-weights System-1 decision engine for software paths that need typed decisions under a time budget (agent routing, tool routing, intent classification, pre-flight guardrails, browser action selection). Not a chat model.

Measured specification

Field	Value
Total parameters	5,003,971
Trainable parameters	3,369,667
Hash-table buffers	1,634,304
d_model	224
Layers	5
Heads	4

Parameter counts match the GitHub README table (verified with verify_claims.py).

Honest claims

Claim	Status
PICA option-order bias = 0.0%	Verified architecturally
Exact parameter table	Verified
FP32 ~0.4 MB for 100k weights	Verified (weight storage only)
p99 < 15ms / ECE < 0.009 / 99.4% arithmetic	Not verified — do not cite from this card
Published latency / accuracy on your workload	Measure yourself

Weights may be lightly or untrained prototypes depending on export; treat behavioral accuracy as unknown until you evaluate on labeled data.

Quickstart

python

from hastejev import HasteJevEngine

eng = HasteJevEngine.from_pretrained("noffy/hastejev-5m")
# eng = HasteJevEngine.from_pretrained("noffy/hastejev-5m", quantization="int4")

r = eng.choice(
    "Request: reset password for user@corp.example",
    ["auth_self_service", "billing", "security_review"],
)
print(r.decision, r.confidence)

Install: pip install git+https://github.com/racstan/hastejev.git

Files

File	Contents
`model.safetensors` / `pytorch_model.bin`	FP32 state dict
`model_fp16.safetensors`	FP16
`model_int8.safetensors`	True weight-only int8 (`weight_q`) when re-exported with ≥1.1.0
`model_int4.safetensors`	True packed int4 (`weight_packed`) when re-exported with ≥1.1.0

Older revisions of model_int8/model_int4 may be mislabeled FP32; re-export or re-download after this commit.

License

Apache-2.0