Text Generation
Safetensors
GGUF
English
dory
decision-making
lora
eider
bf16
nvfp4
llama-cpp
conversational
decision-model
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
- llama.cpp
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
- Pi
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"
Download evaluation/jevman-comparison.json from rdaum/decisive-dory: direct link, hf CLI and curl.
- Browser
- Download file 9.83 kB
-
https://huggingface.co/rdaum/decisive-dory/resolve/main/evaluation/jevman-comparison.json
- Command line
-
hf download hf://rdaum/decisive-dory/evaluation/jevman-comparison.json
-
curl -L -o jevman-comparison.json https://huggingface.co/rdaum/decisive-dory/resolve/main/evaluation/jevman-comparison.json
9.83 kB
| { | |
| "protocol": { | |
| "benchmark": "https://github.com/opper-ai/jevman-benchmark", | |
| "revision": "412ed72484ffeb3bd205a64be2d2ea5e233aac88", | |
| "map": "Original fixed map", | |
| "max_gameplay_seconds": 300, | |
| "parallel_games": 1, | |
| "added_latency_ms": 0, | |
| "local_hardware": "NVIDIA DGX Spark / GB10", | |
| "local_loops": 2, | |
| "local_probability_calibration": false, | |
| "local_server": "Fresh server per game; startup excluded from gameplay", | |
| "hosted_route": "OpenRouter; HTTP latency includes network and provider overhead", | |
| "sampling": "Repeated real-time games; not independent maps or paired random seeds", | |
| "jev_sampling": "All 12 completed games from two six-game runs using the same protocol", | |
| "replay_verification": "All completed replays passed the upstream verifier" | |
| }, | |
| "conditions": [ | |
| { | |
| "model": "Decisive Dory", | |
| "route": "NVFP4 \u00b7 Eider", | |
| "games": [ | |
| { | |
| "score": 2300, | |
| "survived_seconds": 92.66160000000217, | |
| "calls": 191, | |
| "latency_ms_sum": 30752, | |
| "replay_sha256": "ab452665d336a32a32a02f92b1fbe2412afb0107f7d6a664d98a8a6ba8d5afaf" | |
| }, | |
| { | |
| "score": 2040, | |
| "survived_seconds": 97.0343000000044, | |
| "calls": 212, | |
| "latency_ms_sum": 34994, | |
| "replay_sha256": "962baf1ab3627b119e0884158bbb7eb9f47285ea3f40c49179f7cdf376239a22" | |
| }, | |
| { | |
| "score": 2830, | |
| "survived_seconds": 96.17950000000396, | |
| "calls": 195, | |
| "latency_ms_sum": 30941, | |
| "replay_sha256": "77f0471014575ad5c2f27d9878d71297300a9d5038562951f5f7047526fd43e7" | |
| }, | |
| { | |
| "score": 2260, | |
| "survived_seconds": 76.8986000000027, | |
| "calls": 150, | |
| "latency_ms_sum": 24841, | |
| "replay_sha256": "226832364e02185418f46e0b2ae7051fe692f2eb51283c72e2322f42d9a09c15" | |
| }, | |
| { | |
| "score": 2690, | |
| "survived_seconds": 81.84360000000173, | |
| "calls": 159, | |
| "latency_ms_sum": 24517, | |
| "replay_sha256": "6f58daea7fa64b0eb14520b820a30ff6fa1ab21b89add0a31649f3e36899b332" | |
| }, | |
| { | |
| "score": 1910, | |
| "survived_seconds": 67.23850000000128, | |
| "calls": 143, | |
| "latency_ms_sum": 25136, | |
| "replay_sha256": "fd5b20647dd61a04aa71565e5540e3ac0b8d2f25a8878a742790f3af33271982" | |
| } | |
| ], | |
| "game_count": 6, | |
| "mean_score": 2338.3333333333335, | |
| "median_score": 2280.0, | |
| "mean_decision_ms": 163.02952380952382, | |
| "scheduler_errors": 0, | |
| "resolved_models": [ | |
| "local-dory" | |
| ] | |
| }, | |
| { | |
| "model": "Decisive Dory", | |
| "route": "Q8_0 \u00b7 llama.cpp", | |
| "games": [ | |
| { | |
| "score": 2220, | |
| "survived_seconds": 90.00120000000175, | |
| "calls": 151, | |
| "latency_ms_sum": 48905, | |
| "replay_sha256": "97f4bcc396b43e9e8848bd0093977b531aa8193c1871d3f26917c0ea290acb39" | |
| }, | |
| { | |
| "score": 2310, | |
| "survived_seconds": 65.34389999999954, | |
| "calls": 114, | |
| "latency_ms_sum": 40117, | |
| "replay_sha256": "1e9b0d7114f5fa33d5719e8d20bfb89ffdc96d2753e4a128ee31e94797f6ca8f" | |
| }, | |
| { | |
| "score": 2310, | |
| "survived_seconds": 64.91600000000018, | |
| "calls": 114, | |
| "latency_ms_sum": 40300, | |
| "replay_sha256": "efc1ee7b3c96469a866e5aadd94708104a76dbc6520f69dc3247a32a03af412f" | |
| }, | |
| { | |
| "score": 2130, | |
| "survived_seconds": 58.775600000001006, | |
| "calls": 102, | |
| "latency_ms_sum": 35172, | |
| "replay_sha256": "c2ddfdb40daf0a7ca943d6c012690bef8b5ac49f9589681c7e09e9483ad0d002" | |
| }, | |
| { | |
| "score": 2220, | |
| "survived_seconds": 90.04169999999984, | |
| "calls": 153, | |
| "latency_ms_sum": 51135, | |
| "replay_sha256": "c0b76b482c1aabec20cd11b314051537517fedc3012f998995d9a3f0bf0fcd6d" | |
| }, | |
| { | |
| "score": 2980, | |
| "survived_seconds": 87.8558000000031, | |
| "calls": 152, | |
| "latency_ms_sum": 52981, | |
| "replay_sha256": "287970b9664eea214c9c28dd092d1a6dc942430eabc8394a2970360bb357fce5" | |
| } | |
| ], | |
| "game_count": 6, | |
| "mean_score": 2361.6666666666665, | |
| "median_score": 2265.0, | |
| "mean_decision_ms": 341.74300254452925, | |
| "scheduler_errors": 0, | |
| "resolved_models": [ | |
| "dory-jevman-q8" | |
| ] | |
| }, | |
| { | |
| "model": "Jev 1.14", | |
| "route": "OpenRouter", | |
| "games": [ | |
| { | |
| "score": 4770, | |
| "survived_seconds": 66.7314000000021, | |
| "calls": 135, | |
| "latency_ms_sum": 33957, | |
| "replay_sha256": "f33346b8d20393805575649c416a2c4343e9d7c4e6011009188dc5c3b055e662" | |
| }, | |
| { | |
| "score": 2460, | |
| "survived_seconds": 46.36650000000062, | |
| "calls": 95, | |
| "latency_ms_sum": 16876, | |
| "replay_sha256": "2a295eb5464d7ce30be8323147cd936ce40a85473f3a110e7ff5c5c2960827ce" | |
| }, | |
| { | |
| "score": 2540, | |
| "survived_seconds": 45.76800000000065, | |
| "calls": 93, | |
| "latency_ms_sum": 17012, | |
| "replay_sha256": "f8d9967634a0b6a067e158213785c57e51af9ad2763b457e925a28d360110ea5" | |
| }, | |
| { | |
| "score": 6050, | |
| "survived_seconds": 105.78640000000006, | |
| "calls": 204, | |
| "latency_ms_sum": 35635, | |
| "replay_sha256": "b299862de3623ebb332c36646d3d202cda701b0d02495dba118141eb050c12d4" | |
| }, | |
| { | |
| "score": 3020, | |
| "survived_seconds": 65.42200000000238, | |
| "calls": 124, | |
| "latency_ms_sum": 22516, | |
| "replay_sha256": "817ef7cf8f250fcde6d8ef31ac5c511977cc7822e4c80938fbc5a7f9a607e367" | |
| }, | |
| { | |
| "score": 5170, | |
| "survived_seconds": 113.07670000000334, | |
| "calls": 211, | |
| "latency_ms_sum": 41874, | |
| "replay_sha256": "dca22fa9a3b7e7e7adf20fb7350ed04f5b75869e0c7eebecfb9cdef00dc8471e" | |
| }, | |
| { | |
| "score": 3360, | |
| "survived_seconds": 65.91620000000175, | |
| "calls": 115, | |
| "latency_ms_sum": 27609, | |
| "replay_sha256": "f3f2a114c9c196317d76daad98ffeb7760f6ebfeedaec2910369274670d9fcb0" | |
| }, | |
| { | |
| "score": 2510, | |
| "survived_seconds": 56.38020000000047, | |
| "calls": 110, | |
| "latency_ms_sum": 20643, | |
| "replay_sha256": "405afa6aa1e283518d90e4b4e2105be5e79e9c726d2c9d758431e4d0226c231c" | |
| }, | |
| { | |
| "score": 6610, | |
| "survived_seconds": 100.2825000000033, | |
| "calls": 196, | |
| "latency_ms_sum": 33076, | |
| "replay_sha256": "ee10c68d2ef0f7081379508d658bc45ab926cb86a36d5be53105d249ac8f9026" | |
| }, | |
| { | |
| "score": 2400, | |
| "survived_seconds": 50.01130000000068, | |
| "calls": 95, | |
| "latency_ms_sum": 23380, | |
| "replay_sha256": "425ff1f1258f15bad585284621e1ae135d6ab50092b0fedace4915bc9a945365" | |
| }, | |
| { | |
| "score": 2190, | |
| "survived_seconds": 50.25400000000027, | |
| "calls": 88, | |
| "latency_ms_sum": 22038, | |
| "replay_sha256": "49f635dabfa938af30377099bdaa9e43666402997c8a08153b34ce31d570d325" | |
| }, | |
| { | |
| "score": 3370, | |
| "survived_seconds": 78.94970000000323, | |
| "calls": 138, | |
| "latency_ms_sum": 29063, | |
| "replay_sha256": "3cb6f1436d33144467147d9e4ec45fc8d4ce23eb43d571ba3e3cbfc8762ace4a" | |
| } | |
| ], | |
| "game_count": 12, | |
| "mean_score": 3704.1666666666665, | |
| "median_score": 3190.0, | |
| "mean_decision_ms": 201.79488778054863, | |
| "scheduler_errors": 4, | |
| "resolved_models": [ | |
| "typesafe/jev-1.14-20261014" | |
| ] | |
| } | |
| ], | |
| "eider_weights_sha256": "62bc20a6fbafaf157154650dfb4e9ec32a19d67e8e1f60ddcc3318fd37d6ccb4", | |
| "llama_q8_weights_sha256": "bb36b8ed263ce633649ccfad9c6e1dc065e9c3d333624fc27028f496089a38b8", | |
| "base_reference": { | |
| "model": "NVIDIA Dory 1.0 4B (unadapted)", | |
| "route": "NVFP4 \u00b7 Eider", | |
| "games": [ | |
| { | |
| "score": 1490, | |
| "survived_seconds": 48.98480000000033, | |
| "calls": 115, | |
| "latency_ms_sum": 22525, | |
| "replay_sha256": "f06d720ed6fa6881a82cbb58ab0da4446e9553ee620b3d82047872e52577a27c" | |
| }, | |
| { | |
| "score": 680, | |
| "survived_seconds": 35.804200000000534, | |
| "calls": 82, | |
| "latency_ms_sum": 14881, | |
| "replay_sha256": "6eae5fd6214d64446a285712a0e4b76a736edf90b9ea78ebedce31fdb3b1b8c1" | |
| }, | |
| { | |
| "score": 1210, | |
| "survived_seconds": 36.868400000000015, | |
| "calls": 83, | |
| "latency_ms_sum": 13773, | |
| "replay_sha256": "64a36d3e4c9d8c4be8e20caac33c39478f84ca81190151d9538022ef3e744935" | |
| }, | |
| { | |
| "score": 1080, | |
| "survived_seconds": 32.14370000000079, | |
| "calls": 62, | |
| "latency_ms_sum": 10051, | |
| "replay_sha256": "4090ddef29ed6b35294af7153ae6eb46de68a7c2ec60f381c1b5b1ec279c97e7" | |
| }, | |
| { | |
| "score": 1490, | |
| "survived_seconds": 42.16530000000059, | |
| "calls": 90, | |
| "latency_ms_sum": 14641, | |
| "replay_sha256": "155a735437f3788abbddee63382697b0b7b0d47ba4ea0aa77e5f07a2f13254d0" | |
| }, | |
| { | |
| "score": 630, | |
| "survived_seconds": 33.85650000000001, | |
| "calls": 75, | |
| "latency_ms_sum": 13615, | |
| "replay_sha256": "32499a938cc6265eae1f45f313d5962bdb79d8a07e14ee5bcec4d45766e045ea" | |
| } | |
| ], | |
| "game_count": 6, | |
| "mean_score": 1096.6666666666667, | |
| "median_score": 1145.0, | |
| "mean_decision_ms": 176.5009861932939, | |
| "scheduler_errors": 0, | |
| "weights_sha256": "2dc8446f2c52d3249eac5bd2154f1f4a8f206152e3b66d7077965b9ad991bbf7", | |
| "quantization": "Same ModelOpt recipe and calibration examples as Decisive Dory" | |
| } | |
| } | |