Instructions to use rdaum/decisive-dory with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rdaum/decisive-dory with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rdaum/decisive-dory:Q8_0
# Run inference directly in the terminal:
llama cli -hf rdaum/decisive-dory:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rdaum/decisive-dory:Q8_0
# Run inference directly in the terminal:
llama cli -hf rdaum/decisive-dory:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf rdaum/decisive-dory:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf rdaum/decisive-dory:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf rdaum/decisive-dory:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rdaum/decisive-dory:Q8_0

Use Docker

docker model run hf.co/rdaum/decisive-dory:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use rdaum/decisive-dory with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rdaum/decisive-dory"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rdaum/decisive-dory",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rdaum/decisive-dory:Q8_0

Ollama
How to use rdaum/decisive-dory with Ollama:
```
ollama run hf.co/rdaum/decisive-dory:Q8_0
```
Unsloth Desktop

How to use rdaum/decisive-dory with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdaum/decisive-dory:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "rdaum/decisive-dory:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rdaum/decisive-dory with Docker Model Runner:
```
docker model run hf.co/rdaum/decisive-dory:Q8_0
```

Lemonade

How to use rdaum/decisive-dory with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rdaum/decisive-dory:Q8_0

Run and chat with the model

lemonade run user.decisive-dory-Q8_0

List all available models

lemonade list

Hermes Agent

How to use rdaum/decisive-dory with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdaum/decisive-dory:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default rdaum/decisive-dory:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rdaum/decisive-dory with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rdaum/decisive-dory:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "rdaum/decisive-dory:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

decisive-dory / evaluation /README.md

rdaum

Publish Decisive Dory comparisons and JevMan charts

3adea3f verified 5 days ago

preview code

Raw History Blame Contribute Delete

6.43 kB

# Decision evaluation: 512 questions

The model card compares NVFP4 and Q8_0 Dory with hosted models on these questions.
[NVFP4 validation results](modelopt-validation.json) use a separate 1,024-question set.
[Download the questions and targets](questions-512.json).
This is the exact file used for the base Dory, fine-tuned Dory, and hosted-model comparisons in the model card.
| Task | Questions | Source and target |
|---|---:|---|
| State tracking | 192 | SCONE Alchemy and Tangrams: questions about recorded world states after instructions. |
| Planning | 192 | Generated block-stacking and package-delivery problems: simulated legality and search-derived optimal actions. |
| Human judgements | 128 | HelpSteer2: questions with distributions derived from released human ratings and preference votes. |
These examples were withheld from this model's training. Their task families are represented in training.
The results measure performance on this task mix, not general decision-making ability or the source datasets' original benchmarks.
Related examples share a `group_id`; 512 questions should not be interpreted as 512 independent source situations.
Hosted providers' training overlap with these sources is unknown.

## File integrity

SHA-256 of `questions-512.json`:

```text
e2ca7413a306fc2b0e9e044aa685c94d5aa8e0def7cfcec6448941b7369ae625
```

The file is a JSON array. Original identifiers and metadata are preserved so its hash matches the evaluation reports.

## Fields

| Field | Meaning |
|---|---|
| `id` | Unique question identifier. |
| `state` | Context presented to the model. |
| `instructions` | Question or judgement requested. |
| `kind` | `noul` for binary, `choice` for named options, or `score` for ordered levels. |
| `options` | Ordered list of `[answer_name, answer_description]` pairs. Preserve this order. |
| `target` | Target probability for each option, in the same order. Never send these values to the model. |
| `target_basis` | How the reference distribution was constructed. |
| `source`, `dataset`, `domain` | Source and task identifiers. |
| `group_id` | Related source episode, prompt, or canonical planning problem. |
| `tokens`, `labels` | Dory prompt token IDs and corresponding answer-label token IDs used in local evaluation. Other models use their own tokenizers. |
| `role`, `component` | Dataset assembly metadata; not model input. |

## Requests

Send one question at a time with its unchanged `state`, `instructions`, and answer descriptions.
For choice and binary questions, map answer names to descriptions. For scores, send the descriptions as an ordered list.
For example, construct an OpenRouter native decision request from a row as follows:

```python
criteria = (
    [description for name, description in row["options"]]
    if row["kind"] == "score"
    else dict(row["options"])
)
request = {
    "model": model_id,
    "state": row["state"],
    "questions": {
        row["id"]: {
            "type": row["kind"],
            "instructions": row["instructions"],
            "criteria": criteria,
        }
    },
}
```

Hosted comparisons use `/api/alpha/decisions` at OpenRouter. The llama.cpp comparison uses `/v1/systemone`.
Providers control their internal prompts and probability settings. Local Dory evaluations use two recurrent loops and no fitted calibration.
No generated reasoning or additional examples are requested.

## Scoring

Read probabilities in `options` order. For a binary response `p`, use `p` for `true` and `1-p` for `false`.
All reported comparisons require a valid response for every question; no failed questions are omitted.

- **Accuracy:** choose the option with the largest predicted probability. Resolve prediction ties by the original option order. Count it as correct if its target probability is within `1e-6` of the largest target probability.
- **Brier error:** sum `(prediction[i] - target[i])**2` over options, then average over questions. Lower is better. This is a sum over options, not an average over options.
- **Combined results:** average over all 512 questions, rather than averaging the three task scores equally.

Hosted responses are checked for finite probabilities between zero and one and the exact expected options.
If their sum differs from one by at most 0.02, divide by the sum before scoring. Larger discrepancies are rejected.
This handles provider rounding without changing the ordering of answers.
The [hosted comparison report](openrouter-comparison.json) records normalization counts, observed discrepancies, and exact served model versions.

Targets can represent a recorded fact, several equally optimal actions, or disagreement among human raters.
Matching their most probable answer does not by itself establish calibrated confidence.

## Sources, changes, and licences

The evaluation data have separate terms from the model weights' OpenMDW licence.

- **SCONE:** Long, Pasupat, and Liang (2016), [Sequential CONtext-dependent Execution](https://nlp.stanford.edu/projects/scone/), under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/). Episodes and observed states were converted into typed questions and reference distributions. These adapted rows remain under CC BY-SA 4.0.
- **HelpSteer2:** NVIDIA and Scale AI, [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2), under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Prompts, responses, ratings, and preference votes were converted into typed judgement questions and empirical distributions. Source revision: `990b2711a36180dd19d9c94b8627844866f8982a`.
- **Planning:** independently generated block-stacking and delivery problems, inspired by the task families in [PlanBench](https://github.com/karthikv792/LLMs-Planning/tree/main/plan-bench). Published PlanBench instances and generator code were not used. The generated questions and targets are provided by Ryan Daum under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).

Collection and question-format adaptations are provided under CC BY-SA 4.0; the source-specific terms above remain applicable.
[Source provenance](../training-data.json) includes source archive hashes and the split policy.

## Results

- [Base versus fine-tuned Dory, NVFP4 / Eider](base-comparison.json)
- [Base versus fine-tuned Dory, Q8_0 / llama.cpp](llama-comparison.json)
- [Hosted decision models on the same questions](openrouter-comparison.json)

	# Decision evaluation: 512 questions

	The model card compares NVFP4 and Q8_0 Dory with hosted models on these questions.
	[NVFP4 validation results](modelopt-validation.json) use a separate 1,024-question set.

	[Download the questions and targets](questions-512.json).
	This is the exact file used for the base Dory, fine-tuned Dory, and hosted-model comparisons in the model card.

	\| Task \| Questions \| Source and target \|
	\|---\|---:\|---\|
	\| State tracking \| 192 \| SCONE Alchemy and Tangrams: questions about recorded world states after instructions. \|
	\| Planning \| 192 \| Generated block-stacking and package-delivery problems: simulated legality and search-derived optimal actions. \|
	\| Human judgements \| 128 \| HelpSteer2: questions with distributions derived from released human ratings and preference votes. \|

	These examples were withheld from this model's training. Their task families are represented in training.
	The results measure performance on this task mix, not general decision-making ability or the source datasets' original benchmarks.
	Related examples share a `group_id`; 512 questions should not be interpreted as 512 independent source situations.
	Hosted providers' training overlap with these sources is unknown.

	## File integrity

	SHA-256 of `questions-512.json`:

	```text
	e2ca7413a306fc2b0e9e044aa685c94d5aa8e0def7cfcec6448941b7369ae625
	```

	The file is a JSON array. Original identifiers and metadata are preserved so its hash matches the evaluation reports.

	## Fields

	\| Field \| Meaning \|
	\|---\|---\|
	\| `id` \| Unique question identifier. \|
	\| `state` \| Context presented to the model. \|
	\| `instructions` \| Question or judgement requested. \|
	\| `kind` \| `noul` for binary, `choice` for named options, or `score` for ordered levels. \|
	\| `options` \| Ordered list of `[answer_name, answer_description]` pairs. Preserve this order. \|
	\| `target` \| Target probability for each option, in the same order. Never send these values to the model. \|
	\| `target_basis` \| How the reference distribution was constructed. \|
	\| `source`, `dataset`, `domain` \| Source and task identifiers. \|
	\| `group_id` \| Related source episode, prompt, or canonical planning problem. \|
	\| `tokens`, `labels` \| Dory prompt token IDs and corresponding answer-label token IDs used in local evaluation. Other models use their own tokenizers. \|
	\| `role`, `component` \| Dataset assembly metadata; not model input. \|

	## Requests

	Send one question at a time with its unchanged `state`, `instructions`, and answer descriptions.
	For choice and binary questions, map answer names to descriptions. For scores, send the descriptions as an ordered list.
	For example, construct an OpenRouter native decision request from a row as follows:

	```python
	criteria = (
	[description for name, description in row["options"]]
	if row["kind"] == "score"
	else dict(row["options"])
	)
	request = {
	"model": model_id,
	"state": row["state"],
	"questions": {
	row["id"]: {
	"type": row["kind"],
	"instructions": row["instructions"],
	"criteria": criteria,
	}
	},
	}
	```

	Hosted comparisons use `/api/alpha/decisions` at OpenRouter. The llama.cpp comparison uses `/v1/systemone`.
	Providers control their internal prompts and probability settings. Local Dory evaluations use two recurrent loops and no fitted calibration.
	No generated reasoning or additional examples are requested.

	## Scoring

	Read probabilities in `options` order. For a binary response `p`, use `p` for `true` and `1-p` for `false`.
	All reported comparisons require a valid response for every question; no failed questions are omitted.

	- Accuracy: choose the option with the largest predicted probability. Resolve prediction ties by the original option order. Count it as correct if its target probability is within `1e-6` of the largest target probability.
	- Brier error: sum `(prediction[i] - target[i])**2` over options, then average over questions. Lower is better. This is a sum over options, not an average over options.
	- Combined results: average over all 512 questions, rather than averaging the three task scores equally.

	Hosted responses are checked for finite probabilities between zero and one and the exact expected options.
	If their sum differs from one by at most 0.02, divide by the sum before scoring. Larger discrepancies are rejected.
	This handles provider rounding without changing the ordering of answers.
	The [hosted comparison report](openrouter-comparison.json) records normalization counts, observed discrepancies, and exact served model versions.

	Targets can represent a recorded fact, several equally optimal actions, or disagreement among human raters.
	Matching their most probable answer does not by itself establish calibrated confidence.

	## Sources, changes, and licences

	The evaluation data have separate terms from the model weights' OpenMDW licence.

	- SCONE: Long, Pasupat, and Liang (2016), [Sequential CONtext-dependent Execution](https://nlp.stanford.edu/projects/scone/), under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/). Episodes and observed states were converted into typed questions and reference distributions. These adapted rows remain under CC BY-SA 4.0.
	- HelpSteer2: NVIDIA and Scale AI, [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2), under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Prompts, responses, ratings, and preference votes were converted into typed judgement questions and empirical distributions. Source revision: `990b2711a36180dd19d9c94b8627844866f8982a`.
	- Planning: independently generated block-stacking and delivery problems, inspired by the task families in [PlanBench](https://github.com/karthikv792/LLMs-Planning/tree/main/plan-bench). Published PlanBench instances and generator code were not used. The generated questions and targets are provided by Ryan Daum under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).

	Collection and question-format adaptations are provided under CC BY-SA 4.0; the source-specific terms above remain applicable.
	[Source provenance](../training-data.json) includes source archive hashes and the split policy.

	## Results

	- [Base versus fine-tuned Dory, NVFP4 / Eider](base-comparison.json)
	- [Base versus fine-tuned Dory, Q8_0 / llama.cpp](llama-comparison.json)
	- [Hosted decision models on the same questions](openrouter-comparison.json)