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:9931/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://127.0.0.1:9931/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://127.0.0.1:9931/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 research/data/visual/claude/c07.html from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 4.02 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/claude/c07.html
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/research/data/visual/claude/c07.html
-
curl -L -o c07.html https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/claude/c07.html
4.02 kB
| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8"> | |
| <title>Snake</title> | |
| <style> | |
| html,body{margin:0;height:100%;background:#101814;font-family:"Segoe UI",sans-serif;color:#d7f5e0} | |
| body{display:grid;place-items:center} | |
| .wrap{text-align:center} | |
| .hud{display:flex;justify-content:space-between;width:600px;margin:0 auto 10px;font-size:18px} | |
| canvas{background:#16241c;border-radius:12px;box-shadow:0 0 0 3px #24402f,0 20px 50px rgba(0,0,0,.5)} | |
| .hint{opacity:.6;font-size:13px;margin-top:10px} | |
| </style> | |
| </head> | |
| <body> | |
| <div class="wrap"> | |
| <div class="hud"><span>Score: <b id="score">0</b></span><span>Best: <b id="best">0</b></span></div> | |
| <canvas id="c" width="600" height="420"></canvas> | |
| <div class="hint">Arrow keys to steer · Space to restart</div> | |
| </div> | |
| <script> | |
| const C = 20, COLS = 30, ROWS = 21; | |
| const ctx = document.getElementById('c').getContext('2d'); | |
| const scoreEl = document.getElementById('score'), bestEl = document.getElementById('best'); | |
| let snake, dir, nextDir, food, score, best = 0, over; | |
| function reset() { | |
| snake = [{ x: 10, y: 10 }, { x: 9, y: 10 }, { x: 8, y: 10 }]; | |
| dir = nextDir = { x: 1, y: 0 }; | |
| score = 0; over = false; | |
| placeFood(); | |
| } | |
| function placeFood() { | |
| do { food = { x: Math.floor(Math.random() * COLS), y: Math.floor(Math.random() * ROWS) }; } | |
| while (snake.some(s => s.x === food.x && s.y === food.y)); | |
| } | |
| addEventListener('keydown', e => { | |
| const k = { ArrowUp: [0, -1], ArrowDown: [0, 1], ArrowLeft: [-1, 0], ArrowRight: [1, 0] }[e.key]; | |
| if (k && !(k[0] === -dir.x && k[1] === -dir.y)) { nextDir = { x: k[0], y: k[1] }; e.preventDefault(); } | |
| if (e.key === ' ' && over) reset(); | |
| }); | |
| function tick() { | |
| if (over) return; | |
| dir = nextDir; | |
| const head = { x: snake[0].x + dir.x, y: snake[0].y + dir.y }; | |
| if (head.x < 0 || head.y < 0 || head.x >= COLS || head.y >= ROWS || snake.some(s => s.x === head.x && s.y === head.y)) { | |
| over = true; best = Math.max(best, score); bestEl.textContent = best; return; | |
| } | |
| snake.unshift(head); | |
| if (head.x === food.x && head.y === food.y) { score++; scoreEl.textContent = score; placeFood(); } | |
| else snake.pop(); | |
| } | |
| function draw() { | |
| ctx.clearRect(0, 0, 600, 420); | |
| ctx.fillStyle = '#1b2d22'; | |
| for (let x = 0; x < COLS; x++) for (let y = 0; y < ROWS; y++) if ((x + y) % 2) ctx.fillRect(x * C, y * C, C, C); | |
| ctx.fillStyle = '#ff5d5d'; | |
| ctx.beginPath(); ctx.arc(food.x * C + C / 2, food.y * C + C / 2, C * 0.38, 0, Math.PI * 2); ctx.fill(); | |
| snake.forEach((s, i) => { | |
| ctx.fillStyle = i === 0 ? '#7cf2a4' : `hsl(145, 65%, ${55 - Math.min(25, i)}%)`; | |
| ctx.beginPath(); ctx.roundRect(s.x * C + 1, s.y * C + 1, C - 2, C - 2, 6); ctx.fill(); | |
| }); | |
| if (over) { | |
| ctx.fillStyle = 'rgba(0,0,0,.6)'; ctx.fillRect(0, 0, 600, 420); | |
| ctx.fillStyle = '#fff'; ctx.textAlign = 'center'; | |
| ctx.font = 'bold 40px Segoe UI'; ctx.fillText('Game over', 300, 200); | |
| ctx.font = '18px Segoe UI'; ctx.fillText(`Score ${score} — press Space to play again`, 300, 238); | |
| } | |
| } | |
| // a simple autopilot steers towards the food until the player presses a key, so the demo is never idle | |
| let human = false; | |
| addEventListener('keydown', () => { human = true; }, { once: true }); | |
| function autopilot() { | |
| if (human) return; | |
| const h = snake[0], options = [[1, 0], [-1, 0], [0, 1], [0, -1]].filter(([x, y]) => !(x === -dir.x && y === -dir.y)); | |
| const safe = options.filter(([x, y]) => { const n = { x: h.x + x, y: h.y + y }; | |
| return n.x >= 0 && n.y >= 0 && n.x < COLS && n.y < ROWS && !snake.some(s => s.x === n.x && s.y === n.y); }); | |
| const pick = (safe.length ? safe : options).sort((a, b) => | |
| Math.abs(h.x + a[0] - food.x) + Math.abs(h.y + a[1] - food.y) - Math.abs(h.x + b[0] - food.x) - Math.abs(h.y + b[1] - food.y))[0]; | |
| nextDir = { x: pick[0], y: pick[1] }; | |
| } | |
| reset(); | |
| let restarting = false; | |
| setInterval(() => { | |
| autopilot(); tick(); draw(); | |
| if (over && !human && !restarting) { restarting = true; setTimeout(() => { reset(); restarting = false; }, 1200); } | |
| }, 110); | |
| </script> | |
| </body> | |
| </html> | |