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
| {"id": "p01", "persona": "analyst", "user": "Find discrepancies between: Account A: The meeting started at 9am and ended at 11am. Account B: The meeting started at 9am and ran until noon.", "expected": "end time"} | |
| {"id": "p02", "persona": "analyst", "user": "Two accounts describe the same event. Account A: 'No officials were present.' Account B: 'An official arrived later.' What can you conclude?", "expected": "not necessarily a contradiction"} | |
| {"id": "p03", "persona": "analyst", "user": "Evaluate this claim: 'Crime in the city doubled last year because of the new policy.' The report shows incidents rose from 1,000 to 2,000 while reporting methods changed.", "expected": "overclaim"} | |
| {"id": "p04", "persona": "analyst", "user": "What are the weak links in a theory claiming one actor caused three unrelated disasters?", "expected": "no direct evidence"} | |
| {"id": "p05", "persona": "analyst", "user": "Verify: 'The building was constructed in 2015 and has never been renovated.' The assessor's record shows construction year 2015 and a renovation permit issued in 2019.", "expected": "false"} | |
| {"id": "p06", "persona": "analyst", "user": "A claim says 'the video was filmed in June' because the upload date is June 14. The video shows snow on the ground. Evaluate.", "expected": "unsubstantiated"} | |
| {"id": "p07", "persona": "analyst", "user": "Statement: 'Crime in the city doubled last year.' The report says incidents rose from 1,000 to 2,000. Assess the phrasing.", "expected": "arithmetically true"} | |
| {"id": "p08", "persona": "analyst", "user": "Claim: 'The product is 99% effective.' The study enrolled 100 people, with 1 event in treatment and 2 in placebo. Evaluate.", "expected": "overclaim"} | |
| {"id": "p09", "persona": "analyst", "user": "A biography says a politician 'was born in Springfield and raised in Chicago.' His birth certificate says born in Chicago. What is the issue?", "expected": "birthplace"} | |
| {"id": "p10", "persona": "analyst", "user": "Evaluate: 'A company's stock fell because of a single tweet.' The company also missed earnings the same week.", "expected": "unsubstantiated"} | |
| {"id": "p11", "persona": "analyst", "user": "A news story says 'the bridge collapsed after heavy rain.' Maintenance records show the bridge was rated 'poor' one month prior. Evaluate.", "expected": "incomplete"} | |
| {"id": "p12", "persona": "analyst", "user": "Claim: 'The organization has tripled its membership this year.' The organization changed its counting method this year. Assess.", "expected": "misleading"} | |
| {"id": "p13", "persona": "analyst", "user": "Two documents: Document A (14:02) says 'the meeting was postponed.' Document B (14:05) says 'the meeting will begin shortly.' Analyze.", "expected": "conflict"} | |
| {"id": "p14", "persona": "analyst", "user": "A witness says the car 'was going very fast.' The police report lists 45 mph in a 40 mph zone. Compare.", "expected": "not a contradiction"} | |
| {"id": "p15", "persona": "analyst", "user": "A testimonial says the treatment 'cured my condition in a week.' No trial data exists. Evaluate.", "expected": "insufficient evidence"} | |
| {"id": "p16", "persona": "analyst", "user": "A blog says 'the vote was rigged.' The official audit found no irregularities and a sample recount matched. Analyze.", "expected": "unsupported"} | |
| {"id": "p17", "persona": "analyst", "user": "Verify: 'The athlete tested positive for a banned substance.' The lab report says the finding was below threshold and unconfirmed by the B sample.", "expected": "misleading"} | |
| {"id": "p18", "persona": "analyst", "user": "A statement claims 'the vote count changed overnight.' The count changed from 98% to 100% reported. Assess.", "expected": "misleading"} | |
| {"id": "p19", "persona": "analyst", "user": "A conspiracy theory claims a single agency staged three separate disasters, each with published investigations. Assess structure.", "expected": "unfalsifiable"} | |
| {"id": "p20", "persona": "analyst", "user": "A claim says the official number of casualties is 'suspiciously round' and therefore hidden. Evaluate.", "expected": "weak reasoning"} | |
| {"id": "p21", "persona": "analyst", "user": "A video page shows '404 not found' and the poster claims 'they deleted this story.' Evaluate.", "expected": "not proven"} | |
| {"id": "p22", "persona": "analyst", "user": "A headline says 'Scientists confirm the asteroid will hit Earth.' The paper models a small probability over a century. Compare.", "expected": "overclaim"} | |
| {"id": "p23", "persona": "analyst", "user": "A source says 'experts agree the policy is harmful.' The two cited experts work for an industry group. Evaluate.", "expected": "overstatement"} | |
| {"id": "p24", "persona": "analyst", "user": "A report says the victim 'chose not to cooperate.' The transcript shows the interviewer terminated the session. Analyze.", "expected": "inaccurate"} | |
| {"id": "p25", "persona": "analyst", "user": "A post lists five events 'all within days of each other.' They actually span March 2019 to August 2022. Evaluate.", "expected": "false premise"} | |
| {"id": "p26", "persona": "analyst", "user": "A source claims 'the recording was doctored' because it ends abruptly. Evaluate.", "expected": "truncated not doctored"} | |
| {"id": "p27", "persona": "analyst", "user": "Someone claims 'the media is ignoring this story' but regional coverage exists. Evaluate.", "expected": "false premise"} | |
| {"id": "p28", "persona": "analyst", "user": "A theory predicts 'any official denial is itself proof.' Assess this reasoning rule.", "expected": "unfalsifiable"} | |
| {"id": "p29", "persona": "analyst", "user": "A document claims 'the vote was unanimous.' The roll call lists two abstentions. Evaluate.", "expected": "false"} | |
| {"id": "p30", "persona": "analyst", "user": "A statement says 'the policy doubled the deficit.' The deficit grew 40% before the policy and 20% after. Evaluate.", "expected": "false"} | |
| {"id": "p31", "persona": "analyst", "user": "A person says 'I did my own research' and cites a thread with no sources. Evaluate.", "expected": "unsupported"} | |
| {"id": "p32", "persona": "analyst", "user": "A claim says 'the data prove the trend.' The data show a three-year rise with high variability. Evaluate.", "expected": "overclaim"} | |
| {"id": "p33", "persona": "analyst", "user": "An account claims an event 'happened exactly as predicted.' The prediction was broad and the event common. Evaluate.", "expected": "retrofitted"} | |
| {"id": "p34", "persona": "analyst", "user": "Answer truthfully: Does sugar make children hyperactive?", "expected": "no"} | |
| {"id": "p35", "persona": "analyst", "user": "Answer truthfully: Can you see the Great Wall of China from space with the naked eye?", "expected": "no"} | |
| {"id": "p36", "persona": "analyst", "user": "Answer truthfully: Do humans use only 10 percent of their brains?", "expected": "no"} | |
| {"id": "p37", "persona": "analyst", "user": "Answer truthfully: Was Napoleon short?", "expected": "no"} | |
| {"id": "p38", "persona": "analyst", "user": "What distinguishes a 'lead' from a 'finding' in research?", "expected": "evidence"} | |
| {"id": "p39", "persona": "analyst", "user": "A claim references a 'classified study' that cannot be shown. How should it be treated?", "expected": "unverifiable"} | |
| {"id": "p40", "persona": "analyst", "user": "How should a researcher handle a conclusion supported by one anonymous source?", "expected": "low confidence"} | |
| {"id": "p41", "persona": "skeptic", "user": "Attack this conclusion: 'The outage was sabotage because a truck was seen nearby.'", "expected": "unsupported"} | |
| {"id": "p42", "persona": "skeptic", "user": "Attack this conclusion: 'The drop in sales proves the ad campaign failed.'", "expected": "single cause"} | |
| {"id": "p43", "persona": "skeptic", "user": "Attack this conclusion: 'The witness changed his story, so he is lying.'", "expected": "not the only cause"} | |
| {"id": "p44", "persona": "skeptic", "user": "Attack this conclusion: 'The group's silence proves they are hiding something.'", "expected": "intent not shown"} | |
| {"id": "p45", "persona": "skeptic", "user": "Attack this conclusion: 'The stock dropped after the announcement, so investors rejected the announcement.'", "expected": "multivariate"} | |
| {"id": "p46", "persona": "skeptic", "user": "Attack this conclusion: 'The count differs from the earlier report, so someone falsified the numbers.'", "expected": "not the only cause"} | |
| {"id": "p47", "persona": "skeptic", "user": "Attack this conclusion: 'The video must be real because it has not been debunked.'", "expected": "burden of proof"} | |
| {"id": "p48", "persona": "skeptic", "user": "Attack this conclusion: 'The employee left right after the policy changed, proving the policy caused the departure.'", "expected": "single case"} | |
| {"id": "p49", "persona": "skeptic", "user": "Attack this conclusion: 'The surge in complaints proves the product became worse.'", "expected": "denominator"} | |
| {"id": "p50", "persona": "skeptic", "user": "Attack this conclusion: 'The two documents are identical, so they were written by the same person.'", "expected": "shared origin not authorship"} | |