Instructions to use FerrellSyntheticIntelligence/fsi-anomaly 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 FerrellSyntheticIntelligence/fsi-anomaly 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 FerrellSyntheticIntelligence/fsi-anomaly # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/fsi-anomaly
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf FerrellSyntheticIntelligence/fsi-anomaly # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/fsi-anomaly
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 FerrellSyntheticIntelligence/fsi-anomaly # Run inference directly in the terminal: ./llama-cli -hf FerrellSyntheticIntelligence/fsi-anomaly
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 FerrellSyntheticIntelligence/fsi-anomaly # Run inference directly in the terminal: ./build/bin/llama-cli -hf FerrellSyntheticIntelligence/fsi-anomaly
Use Docker
docker model run hf.co/FerrellSyntheticIntelligence/fsi-anomaly
- LM Studio
- Jan
- Ollama
How to use FerrellSyntheticIntelligence/fsi-anomaly with Ollama:
ollama run hf.co/FerrellSyntheticIntelligence/fsi-anomaly
- Unsloth Desktop
- Docker Model Runner
How to use FerrellSyntheticIntelligence/fsi-anomaly with Docker Model Runner:
docker model run hf.co/FerrellSyntheticIntelligence/fsi-anomaly
- Lemonade
How to use FerrellSyntheticIntelligence/fsi-anomaly with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull FerrellSyntheticIntelligence/fsi-anomaly
Run and chat with the model
lemonade run user.fsi-anomaly-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
| """eval_summary parses persisted per-probe lines into the honest scorecard.""" | |
| from pathlib import Path | |
| from research.eval_summary import scored_ids, summarize | |
| FIXTURE = """\ | |
| == eval ckpt/hybrid50m_v22_lora/best.pt == | |
| [p01] 0.00 | verdict: true | conf: HIGH | |
| [p05] 1.00 | verdict: false | conf: HIGH | |
| [p07] 1.00 | verdict: true | conf: HIGH | |
| [p38] qual | verdict: false | conf: HIGH | |
| [verdict-00] 1.00 | verdict: true | conf: HIGH | |
| [discrepancy-06] 0.00 | verdict: false | conf: HIGH | |
| """ | |
| def test_summarize_exact(tmp_path): | |
| log = tmp_path / "battery.log" | |
| log.write_text(FIXTURE) | |
| out = summarize(str(log)) | |
| # p01 expected refutes -> 0; p05 false -> 1; p07 true -> 1; p38 qualitative | |
| # verdict-00 true -> 1; discrepancy-06 false -> 1 | |
| assert out["n"] == 5 | |
| assert out["qualitative"] == 1 | |
| assert out["accuracy"] == 0.8 | |
| assert out["by_category"]["generic"] == 2 / 3 | |
| assert out["by_category"]["discrepancy"] == 1.0 | |
| def test_summarize_dedupes_resume_sections(tmp_path): | |
| log = tmp_path / "battery.log" | |
| log.write_text(FIXTURE + "== eval ckpt/hybrid50m_v22_lora/best.pt ==\n" | |
| "[p01] 0.00 | verdict: true | conf: HIGH\n") | |
| out = summarize(str(log)) | |
| assert out["n"] == 5 # p01 counted once | |
| def test_scored_ids_whole_file(tmp_path): | |
| log = tmp_path / "battery.log" | |
| log.write_text(FIXTURE) | |
| ids = scored_ids(str(log)) | |
| assert "p01" in ids and "verdict-00" in ids and "discrepancy-06" in ids | |
| assert "resume" not in ids # attempt headers / resume lines are ignored | |