tamev: open AI decision model by Tamkimd

Q: How do I run tamev?

Pull the weights with systemone pull tamkimd/tamev and load them with the runtime named in the manifest.

TAMEV-Micro-MiniLM

Small encoder decision models: a state, a typed question and your option list in, a probability per option out, in one forward pass on CPU. choice, noul and score share one call. Headline Micro tier is 22.8M params on MiniLM; the maker says accuracy holds only in-distribution.

A decoupled bi-encoder with a bilinear pointer head shared across option slots, so option order cannot change the answer; options are passed per call. The maker warns that top-1 is near chance outside the training distribution, so fine-tune before use; the published numbers are on an in-distribution held-out set. Weights have been replaced several times, so pin a revision; trust_remote_code is required. The training data includes Yelp and Amazon reviews, which carry upstream terms. Siblings nano-tinybert, nano-flash-tinybert and small-modernbert; larger Qwen tiers are announced without weights. A TorchScript file in the repo is flagged by the Hub scanner and is not listed here.

What it decides

choice — picks one option from a set
score — places the input on an ordered scale
noul — answers a yes/no question with one probability

At a glance


Parameters	22.8M
Base model	`sentence-transformers/all-MiniLM-L6-v2`
Maker	Tamkimd
Released	2026-09-25
License	apache-2.0
Reported accuracy	82.2%
Reported latency	7.29 ms p50 / 13.07 ms p95 on one CPU thread on an Apple M4, warm option cache

Get the weights

pip install systemonemodels
systemone pull tamkimd/tamev

The files are served from the maker's Hugging Face repository, Tamkimd/tamev-micro-minilm, and verified against the checksums recorded here.

Playground

Build a request for tamkimd/tamev. The form and the JSON are the same object; the response panel shows the shape every System One server returns.

Input

StateThe context the questions are asked about. Up to the model's context length.

A yes/no question. The answer is one probability that the condition holds.

Instructions

Response

Placeholder values, in the shape a run returns.

safenoul7%

This model doesn't answer live here. Send this request to your own server for this model; every System One server speaks this shape.

Call it

curl https://api.systemonemodels.ai/v1/systemone \
  -H "Authorization: Bearer $SYSTEMONE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"tamkimd/tamev","state":"Task: clean up inactive accounts before the quarterly report.\nProposed tool call: delete_rows(table=\"customers\", where=\"last_login < 2023-01-01\")\nContext: the customers table is production; there is no backup newer than Friday.","questions":{"safe":{"type":"noul","instructions":"Is this action safe to run without a human approving it first?"}}}'

Providers

Where this model runs today. Call the provider directly or run the weights yourself.

Provider	Status	Input	Output	Context	Link
Your own hardware	Open weights	Free	Free	128	`systemone pull tamkimd/tamev`

Pricing

Availability: Open weights
Licence: apache-2.0
Hosted API: None recorded. Pull the weights and run it yourself.

Pulling and running the weights costs nothing beyond your own hardware; the licence above says what you may do with them.

Performance

Decision accuracy	82.2%
Calibration error (ECE)	0.022
Median latency	7.3 ms
p95 latency	13.1 ms

Suite: TAMEV held-out set (19,999 typed-decision items re-formed from public datasets; in-distribution, the maker's own). Numbers are the publisher's own, from the manifest; the model card says how they were measured.

config.json772 B
configuration_tamev.py1.9 kB
deployment_manifest.json2.2 kB
LICENSE724 B
model_fp16.onnxa8c6bcd44 MB
model_index.json3.0 kB
model_int8.onnx7f3ef0622 MB
model.onnx5a69ec587 MB
model.safetensorsc7a8a1287 MB
modeling_tamev.py22 kB
tamev_mlx_config.json653 B
tokenizer_config.json594 B
tokenizer.json695 kB

Every file resolves through a stable path — /v1/models/tamkimd/tamev/resolve/2026.09/<path> — while the object underneath is content-addressed and shared with every other version that holds the same bytes. API reference.

Model tree

Every ancestor down to this model, then what was built on it, wherever each one lives.

Activity

Downloads0

Stars0

Versions1

Built with it0

Latest version: 2026.09
Updated: Oct 7, 2026
Added to the registry: Oct 7, 2026
Mirrors: tamkimd/tamev-micro-minilm

Documentation

The HTTP API — every endpoint the website and CLI use.
The CLI — pull this model with systemone pull tamkimd/tamev.
systemone.yaml — what the manifest below records.

systemone.yaml

{
  "spec_version": "0.1",
  "model": "tamev",
  "namespace": "tamkimd",
  "category": "system-one",
  "architecture": "tamev",
  "base_model": "sentence-transformers/all-minilm-l6-v2",
  "base_model_source": "huggingface",
  "license": "apache-2.0",
  "license_name": null,
  "summary": "Small encoder decision models: a state, a typed question and your option list in, a probability per option out, in one forward pass on CPU. choice, noul and score share one call. Headline Micro tier is 22.8M params on MiniLM; the maker says accuracy holds only in-distribution.",
  "tags": [
    "system-one",
    "encoder",
    "bi-encoder",
    "minilm",
    "cpu",
    "onnx",
    "22.8m"
  ],
  "capabilities": [
    "choice",
    "score",
    "noul"
  ],
  "runtime": {
    "framework": "pytorch",
    "entrypoint": null,
    "python": null,
    "hardware": "cpu"
  },
  "artifacts": [],
  "evaluation": {
    "suite": "TAMEV held-out set (19,999 typed-decision items re-formed from public datasets; in-distribution, the maker's own)",
    "suite_version": null,
    "decision_accuracy": 0.8223,
    "calibration_error": 0.0224,
    "valid_action_rate": null,
    "median_latency_ms": 7.29,
    "p95_latency_ms": 13.07
  },
  "parameters": 22800000,
  "context_length": 128,
  "hub_repo": "Tamkimd/tamev-micro-minilm",
  "released": "2026-09-25",
  "availability": "open-weights",
  "hosted": null
}

View raw metadata

FAQ

What does tamev decide?

It answers 3 kinds of question: choice picks one option from a list you give it; score rates the state on a scale you define; noul returns the probability that a condition holds. Every answer is a typed value with a probability, never free text.

How do I run tamev?

Pull the weights with systemone pull tamkimd/tamev and load them with the runtime named in the manifest.

Can I use tamev commercially?

It is published under apache-2.0. Read the licence before shipping; the model card may add terms of its own.

What is tamev built on?

Its base model is sentence-transformers/all-minilm-l6-v2, a tamev architecture. The Model tree section shows the whole chain.

How much can tamev read at once?

Up to 128 tokens of state per request. The model has 23M parameters.

How accurate is tamev?

Its publisher reports 82.2% decision accuracy on TAMEV held-out set (19,999 typed-decision items re-formed from public datasets; in-distribution, the maker's own). Suites differ between publishers, so compare models on your own labelled examples.

How do I link to tamev?

This page is https://systemonemodels.ai/tamkimd/tamev. Its metadata is at https://api.systemonemodels.ai/v1/models/tamkimd/tamev and a Markdown summary for agents at https://systemonemodels.ai/tamkimd/tamev.md.

Tamkimd: tamev

TAMEV-Micro-MiniLM

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ

Tamkimd: tamev

TAMEV-Micro-MiniLM

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ