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
| """Build domain-adaptation corpus: analyst/forensic chat text + playbooks + a | |
| small story mix for fluency. Output: data/domain_full.txt (one text blob per line).""" | |
| import json, random, re | |
| from pathlib import Path | |
| rng = random.Random(20260802) | |
| def load(p): | |
| return [json.loads(l) for l in open(p, encoding="utf-8") if l.strip()] | |
| def lines_from_jsonl(p, out): | |
| for r in load(p): | |
| if "raw" in r and r.get("raw"): | |
| out.append(r["raw"]) | |
| elif r.get("user") and r.get("assistant"): | |
| p_tok = {"analyst": "<|analyst|>", "skeptic": "<|skeptic|>", "none": ""}.get(r.get("persona", "analyst"), "<|analyst|>") | |
| out.append(f"{p_tok}<|user|>{r['user']}<|assistant|>{r['assistant']}<|endoftext|>") | |
| def paragraphs(p, out): | |
| for para in re.split(r"\n\s*\n", Path(p).read_text(encoding="utf-8")): | |
| para = " ".join(para.split()) | |
| if len(para) > 40: | |
| out.append(para) | |
| def main(): | |
| out = [] | |
| for f in ["sft_forensic.jsonl", "sft_sop_mix.jsonl", "sft_sop.jsonl", "sft_distill_mix.jsonl", | |
| "general_chat.jsonl", "persona_dialogue.jsonl", "tool_use.jsonl", | |
| "distill_analyst_a.jsonl", "distill_analyst_b.jsonl", "distill_dialogue.jsonl", | |
| "distill_method.jsonl", "distill_qa.jsonl", "distill_skeptic.jsonl"]: | |
| lines_from_jsonl(f"data/{f}", out) | |
| for f in ["library/the_prince.txt", "library/verification_playbook.txt", "library/manipulation_playbook.txt"]: | |
| paragraphs(f"data/{f}", out) | |
| rng.shuffle(out) | |
| # story mix: reservoir sample for fluency (10% by count) | |
| story = [] | |
| with open("data/TinyStoriesV2-GPT4-train.txt", encoding="utf-8") as fh: | |
| for i, line in enumerate(fh): | |
| s = line.strip() | |
| if not s: | |
| continue | |
| if len(story) < 900: | |
| story.append(s) | |
| else: | |
| j = rng.randrange(i + 1) | |
| if j < 900: | |
| story[j] = s | |
| rng.shuffle(story) | |
| final = out + story[:900] | |
| rng.shuffle(final) | |
| Path("data/domain_full.txt").write_text("\n".join(final), encoding="utf-8") | |
| print(f"domain lines: {len(final):,} (domain {len(out):,} + story {min(900,len(story)):,})", flush=True) | |
| if __name__ == "__main__": | |
| main() | |