Safetensors
GGUF
English
Russian
lfm3
reasoning
test-time-compute
inference-time-scaling
code-generation
llama.cpp
negative-results
conversational
Instructions to use HelioAI/LFM3-1.7B-inference-modules-experiments 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 HelioAI/LFM3-1.7B-inference-modules-experiments 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 HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M # Run inference directly in the terminal: llama cli -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M # Run inference directly in the terminal: llama cli -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Use Docker
docker model run hf.co/HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with Ollama:
ollama run hf.co/HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
- Unsloth Desktop
- Pi
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with Docker Model Runner:
docker model run hf.co/HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
- Lemonade
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Run and chat with the model
lemonade run user.LFM3-1.7B-inference-modules-experiments-Q5_K_M
List all available models
lemonade list
- Hermes Agent
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use HelioAI/LFM3-1.7B-inference-modules-experiments with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "HelioAI/LFM3-1.7B-inference-modules-experiments:Q5_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download runtime/vis_autofix.py from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 2.74 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/runtime/vis_autofix.py
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/runtime/vis_autofix.py
-
curl -L -o vis_autofix.py https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/runtime/vis_autofix.py
2.74 kB
| """Deterministic fixes of visual answers before rendering (no model call), measured on recorded runs. | |
| importmap the page loads three.js as ES modules (imports from 'three', 'three/addons/...' or from the unpkg URL, | |
| whose addons import the bare name 'three') but has no import map: insert the import map of the task | |
| at the start of <head>. | |
| usage: vis_autofix.py --src results/vis_rep/vis.jsonl --out results/vis_rep_fix/vis.jsonl | |
| Records whose answer is changed get "autofix": [...]; the rest are copied unchanged (exactly paired). | |
| """ | |
| import argparse | |
| import json | |
| import os | |
| import re | |
| import sys | |
| sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) | |
| from render import extract # noqa: E402 | |
| IMPORT_MAP = ('<script type="importmap">{"imports": {"three": "https://unpkg.com/three@0.160.0/build/three.module.js", ' | |
| '"three/addons/": "https://unpkg.com/three@0.160.0/examples/jsm/"}}</script>') | |
| USES_THREE_MODULE = re.compile(r"""from\s+['"](three|three/addons/[^'"]+|https://unpkg\.com/three@[^'"]+)['"]""") | |
| def fix_importmap(src): | |
| if 'type="importmap"' in src or "type='importmap'" in src or not USES_THREE_MODULE.search(src): | |
| return src | |
| m = re.search(r"<head[^>]*>", src, re.I) | |
| if m: | |
| return src[:m.end()] + "\n" + IMPORT_MAP + src[m.end():] | |
| m = re.search(r"<script", src, re.I) | |
| return src[:m.start()] + IMPORT_MAP + "\n" + src[m.start():] if m else src | |
| def autofix(text, kind): | |
| """Returns (new answer text, list of applied fixes).""" | |
| if kind != "html" or text is None: | |
| return text, [] | |
| src = extract(text, kind) | |
| if not src: | |
| return text, [] | |
| new = fix_importmap(src) | |
| if new == src: | |
| return text, [] | |
| return text.replace(src, new), ["importmap"] | |
| if __name__ == "__main__": | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--src", required=True) | |
| ap.add_argument("--out", required=True) | |
| ap.add_argument("--tasks", default="data/visual/tasks.jsonl") | |
| a = ap.parse_args() | |
| tasks = {json.loads(l)["id"]: json.loads(l) for l in open(a.tasks, encoding="utf-8")} | |
| os.makedirs(os.path.dirname(a.out), exist_ok=True) | |
| n = 0 | |
| with open(a.out, "w", encoding="utf-8") as f: | |
| for l in open(a.src, encoding="utf-8"): | |
| r = json.loads(l) | |
| c = r["completion"] | |
| if "</think>" in c: | |
| head, fin = c.split("</think>", 1) | |
| new, fixes = autofix(fin, tasks[r["id"]]["kind"]) | |
| if fixes: | |
| r = {**r, "completion": head + "</think>" + new, "autofix": fixes} | |
| n += 1 | |
| f.write(json.dumps(r, ensure_ascii=False) + "\n") | |
| print(f"{n} answers changed -> {a.out}") | |