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
| {"user":"Verify: 'The company reported a net profit of 8 million dollars last year.' The audited statement shows a net loss of 3 million dollars for that year.","assistant":"<|scratchpad|>The claim asserts a net profit of 8 million dollars. The audited financial statement, the authoritative record for the period, shows a net loss of 3 million dollars. The claimed figure and the record disagree in sign and magnitude. <|final|>I consider this false. The audited statement records a net loss of 3 million dollars for the year, which contradicts the claimed profit of 8 million. The record is authoritative and directly checkable."} | |
| {"user":"Verify: 'The vote was unanimous.' The recorded roll call shows 12 in favor and 2 opposed.","assistant":"<|scratchpad|>The claim says the vote was unanimous. The roll call is the primary record and shows 12 in favor and 2 opposed. A vote with two dissenting votes is by definition not unanimous. <|final|>I consider this false. The roll call records two opposed votes, so the vote was not unanimous. The primary record contradicts the claim directly."} | |
| {"user":"Verify: 'The dam is 60 meters tall.' The engineering survey measures the dam at 43 meters.","assistant":"<|scratchpad|>The claim gives a specific height of 60 meters. The engineering survey is the direct measurement record and measures 43 meters. The figures differ substantially. <|final|>I consider this false. The survey measures the dam at 43 meters, not 60. The claim's figure does not match the measured record."} | |
| {"user":"Verify: 'The museum closed in 2019.' The museum's public record shows it closed in 2021.","assistant":"<|scratchpad|>The claim states the museum closed in 2019. The museum's public record shows closure in 2021. The years conflict by two years. <|final|>I consider this false. The public record dates the closure to 2021, which contradicts the claimed 2019. The record is checkable and specific."} | |
| {"user":"Verify: 'The train arrives at 14:05.' The published timetable lists the arrival at 14:35.","assistant":"<|scratchpad|>The claim gives an arrival time of 14:05. The published timetable lists 14:35. A half-hour discrepancy exists between claim and record. <|final|>I consider this false. The timetable lists the arrival at 14:35, not 14:05. The claimed time does not match the published record."} | |
| {"user":"Verify: 'The painting was restored in 1988.' The conservation log dates the restoration to 1995.","assistant":"<|scratchpad|>The claim dates the restoration to 1988. The conservation log is the authoritative record and dates it to 1995. Seven years separate the claim from the log. <|final|>I consider this false. The conservation log records the restoration in 1995, which contradicts the claimed 1988. The log is the primary record for conservation work."} | |
| {"user":"Verify: 'Sales doubled year over year.' The company's filings show sales grew from 40 thousand to 55 thousand units.","assistant":"<|scratchpad|>The claim asserts sales doubled. The filings show growth from 40 thousand to 55 thousand units. A rise from 40 to 55 is an increase of 37.5 percent, not a doubling. <|final|>I consider this false. Sales grew from 40 thousand to 55 thousand units, a 37.5 percent increase, not a doubling. The filings do not support the claim's magnitude."} | |