jrlabs01/ s1

8 Downloads Updated 2 days ago

s1: an open, calibrated System One decision model

vision tools thinking

ollama run jrlabs01/s1

curl http://localhost:11434/api/chat \
  -d '{
    "model": "jrlabs01/s1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='jrlabs01/s1',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'jrlabs01/s1',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model jrlabs01/s1

OpenCode

OpenCode ollama launch opencode --model jrlabs01/s1

Hermes Agent

Hermes Agent ollama launch hermes --model jrlabs01/s1

OpenClaw

OpenClaw ollama launch openclaw --model jrlabs01/s1

Models

Name

1 model

Size / Usage

Context

Input

s1:latest

18GB · 256K context window · Text, Image · 2 days ago

s1:latest

18GB

256K

Text, Image

Readme

s1: an open, calibrated System One decision model

s1 makes typed decisions over text or JSON (pick an option, answer yes/no, or place something on an ordered scale) and gives a calibrated probability for every option, from one forward pass. This is the int4 build of j-raghavan/s1-gemma4-26b-decision, a fine-tune of Gemma 4 26B-A4B. Apache-2.0.

Accuracy of this build (held-out test sets): JevBench subset 0.801 (bf16: 0.808), structured decisions 0.966 (bf16: 0.971); neither difference is significant. About 26 GB of memory while loaded.

Use it the right way

s1 reads the probabilities of the option letters after the prefix Answer:. Send raw prompts that start with <bos>; Ollama’s chat formatting changes the prompt and the answers.

The easiest way is the repository’s HTTP API, which does this for you and adds calibration:

ollama pull jrlabs01/s1
git clone https://github.com/j-raghavan/s1-decision-model && cd s1-decision-model
S1_MODEL=jrlabs01/s1 uv run --extra api uvicorn api.server:app --port 8000
curl -s localhost:8000/v1/decisions -H 'content-type: application/json' -d '{
  "state": {"ticket": "I was charged twice for order 4471."},
  "questions": {"team": {"type": "choice", "instructions": "Which team should handle this?",
    "criteria": {"billing": "Payments and refunds", "shipping": "Deliveries", "tech": "Bugs"}}}}'

Calling Ollama directly: POST /api/generate with "raw": true, "logprobs": true, "top_logprobs": 20, "options": {"num_predict": 1, "temperature": 0} and the prompt format in examples/quickstart.py, prefixed with <bos>.

Benchmarks, methodology and training data: github.com/j-raghavan/s1-decision-model. s1 is an independent project, not affiliated with TypeSafe AI (Jev).

# s1: an open, calibrated System One decision model

s1 makes typed decisions over text or JSON (pick an option, answer yes/no, or place something on an ordered scale) and
gives a calibrated probability for every option, from one forward pass. This is the int4 build of
[j-raghavan/s1-gemma4-26b-decision](https://huggingface.co/j-raghavan/s1-gemma4-26b-decision), a fine-tune of Gemma 4
26B-A4B. Apache-2.0.

**Accuracy of this build** (held-out test sets): JevBench subset 0.801 (bf16: 0.808), structured decisions 0.966
(bf16: 0.971); neither difference is significant. About 26 GB of memory while loaded.

## Use it the right way

s1 reads the probabilities of the option letters after the prefix `Answer:`. Send **raw** prompts that **start with
`<bos>`**; Ollama's chat formatting changes the prompt and the answers.

The easiest way is the repository's HTTP API, which does this for you and adds calibration:

```bash
ollama pull jrlabs01/s1
git clone https://github.com/j-raghavan/s1-decision-model && cd s1-decision-model
S1_MODEL=jrlabs01/s1 uv run --extra api uvicorn api.server:app --port 8000
curl -s localhost:8000/v1/decisions -H 'content-type: application/json' -d '{
  "state": {"ticket": "I was charged twice for order 4471."},
  "questions": {"team": {"type": "choice", "instructions": "Which team should handle this?",
    "criteria": {"billing": "Payments and refunds", "shipping": "Deliveries", "tech": "Bugs"}}}}'
```

Calling Ollama directly: `POST /api/generate` with `"raw": true`, `"logprobs": true`, `"top_logprobs": 20`,
`"options": {"num_predict": 1, "temperature": 0}` and the prompt format in
[examples/quickstart.py](https://github.com/j-raghavan/s1-decision-model/blob/main/examples/quickstart.py), prefixed
with `<bos>`.

Benchmarks, methodology and training data: [github.com/j-raghavan/s1-decision-model](https://github.com/j-raghavan/s1-decision-model).
s1 is an independent project, not affiliated with TypeSafe AI (Jev).

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)