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
| """Full-project backup to Hugging Face (continuity snapshot). | |
| Pushes the entire workspace (code, data, notes, pipeline, checkpoints) to | |
| FerrellSyntheticIntelligence/fsi-anomaly so work can continue on another | |
| machine. Skips .venv and python caches. Resume-safe: a local manifest | |
| (logs/hf_backup_manifest.json) records uploaded files by sha256, and files | |
| already present on the Hub are skipped, so re-running after an interruption | |
| continues where it stopped. Progress is visible per commit. | |
| Usage: | |
| HF_TOKEN=hf_xxx .venv/bin/python hf_backup.py # everything | |
| HF_TOKEN=hf_xxx .venv/bin/python hf_backup.py --stage ckpt # checkpoints only | |
| """ | |
| import argparse | |
| import hashlib | |
| import json | |
| import os | |
| import sys | |
| from pathlib import Path | |
| from huggingface_hub import CommitOperationAdd, HfApi | |
| HERE = Path(__file__).resolve().parent | |
| EXCLUDED_DIRS = {".venv", "__pycache__", ".pytest_cache"} | |
| EXCLUDED_SUFFIXES = {".pyc"} | |
| MANIFEST = HERE / "logs" / "hf_backup_manifest.json" | |
| BATCH_FILES = 100 | |
| BATCH_BYTES = 800_000_000 # ~800MB per commit (safer on tablet network) | |
| def sha256(path: Path) -> str: | |
| h = hashlib.sha256() | |
| with open(path, "rb") as f: | |
| for chunk in iter(lambda: f.read(1 << 20), b""): | |
| h.update(chunk) | |
| return h.hexdigest() | |
| def iter_files(stage: str): | |
| for p in sorted(HERE.rglob("*")): | |
| if not p.is_file(): | |
| continue | |
| rel = p.relative_to(HERE).as_posix() | |
| parts = rel.split("/") | |
| if any(part in EXCLUDED_DIRS for part in parts): | |
| continue | |
| if p.suffix in EXCLUDED_SUFFIXES: | |
| continue | |
| if rel == "logs/hf_backup_manifest.json": | |
| continue | |
| if stage == "small" and parts[0] == "ckpt": | |
| continue | |
| if stage == "ckpt" and parts[0] != "ckpt": | |
| continue | |
| yield rel, p | |
| def main(): | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--repo", default="FerrellSyntheticIntelligence/fsi-anomaly") | |
| ap.add_argument("--stage", choices=["all", "small", "ckpt"], default="all") | |
| args = ap.parse_args() | |
| token = os.environ.get("HF_TOKEN") | |
| if not token: | |
| sys.exit("HF_TOKEN env var required") | |
| api = HfApi(token=token) | |
| try: | |
| api.repo_info(args.repo, repo_type="model") | |
| print(f"repo exists: {args.repo}", flush=True) | |
| except Exception: | |
| api.create_repo(args.repo, private=True, repo_type="model") | |
| print(f"created repo: {args.repo} (private)", flush=True) | |
| manifest = {} | |
| if MANIFEST.exists(): | |
| try: | |
| manifest = json.loads(MANIFEST.read_text()) | |
| except json.JSONDecodeError: | |
| manifest = {} | |
| remote = set(api.list_repo_files(args.repo, repo_type="model")) | |
| print(f"remote files already present: {len(remote)}", flush=True) | |
| ops = [] | |
| batch_bytes = 0 | |
| n_uploaded = 0 | |
| n_skipped = 0 | |
| def flush(reason): | |
| nonlocal ops, batch_bytes, n_uploaded | |
| if not ops: | |
| return | |
| api.create_commit( | |
| repo_id=args.repo, | |
| operations=ops, | |
| commit_message=f"backup {args.stage}: {len(ops)} files ({reason})", | |
| repo_type="model", | |
| ) | |
| for op in ops: | |
| manifest[op.path_in_repo] = sha256(Path(op.path_or_fileobj)) | |
| MANIFEST.write_text(json.dumps(manifest, indent=0)) | |
| n_uploaded += len(ops) | |
| print(f"committed {len(ops)} files -> {n_uploaded} total ({reason})", flush=True) | |
| ops = [] | |
| batch_bytes = 0 | |
| for rel, p in iter_files(args.stage): | |
| if rel in remote or manifest.get(rel) == sha256(p): | |
| n_skipped += 1 | |
| continue | |
| ops.append(CommitOperationAdd(path_in_repo=rel, path_or_fileobj=str(p))) | |
| batch_bytes += p.stat().st_size | |
| if len(ops) >= BATCH_FILES or batch_bytes >= BATCH_BYTES: | |
| flush("batch") | |
| flush("final") | |
| print(f"DONE stage={args.stage}: uploaded={n_uploaded} skipped={n_skipped}", flush=True) | |
| print(f"repo: https://huggingface.co/{args.repo}", flush=True) | |
| if __name__ == "__main__": | |
| main() | |