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 research/data/visual/mentor_hints.json from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 3.41 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/mentor_hints.json
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/research/data/visual/mentor_hints.json
-
curl -L -o mentor_hints.json https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/mentor_hints.json
3.41 kB
| { | |
| "s04": "A chart needs a scale. First fix a plot area inside the viewBox (for example x from 70 to 570 and y from 50 to 330 in a 620x400 viewBox), then map every value with arithmetic: x_i = 70 + i * 500 / 6 for day i, and y = 330 - (value - 10) * 280 / 15 for prices between 10 and 25. Write the computed numbers out in your reasoning before writing the SVG. Draw the x and y axes on the edges of the plot area, a grid line and a label (text-anchor=\"end\") for every 5, the day labels under the x axis, the polyline and the dots at the computed points, and the title centred above the plot area.", | |
| "s05": "A car is not a rectangle: draw the body as one <path> silhouette - a long low hood at the front, a cabin raised in the middle with a sloped windshield, and a short sloping rear. Place the wheels at about 20% and 80% of the body length, with their bottoms exactly on the road line, and draw them after the body so they overlap its lower edge. The windshield and the side window are polygons that follow the slope of the cabin. Put a small yellow headlight at the very front and a red tail light at the very back.", | |
| "s06": "In SVG the y axis points down, so 'up' means a smaller y. Anchor every part to the one below it: the hull is a trapezoid (wider at the top) whose bottom sits in the water line; the mast is a vertical line from the middle of the hull's top edge up to near the top of the picture; each sail is a vertical triangle with one edge along the mast (one to the left of the mast, one to the right), so the sails stand upright; the flag is a small triangle at the top of the mast. Draw the sky, then the sun, then the boat, then the waves (a filled blue path with a wavy top edge) last so the hull sits in the water.", | |
| "s07": "Plan the proportions before drawing: the body is a tall brown ellipse; in its upper part two big white eye discs, each about a third of the body's width, almost touching; black pupils about half the eye radius and a small white highlight in each pupil; an orange triangular beak between and just below the eyes. The wings are darker brown ellipses overlapping the left and right sides of the body (not another colour). The branch is a thick brown bar under the body, and the orange feet (three short toes each) are drawn on top of the branch so they grip it.", | |
| "s08": "Build the rocket around one vertical centre line x = cx so that every part touches the next: the body is a tall white rounded rectangle centred on cx; the red nose cone is a triangle whose base is exactly the top edge of the body and whose tip is on cx; the two red fins are triangles that share an edge with the lower left and right sides of the body; the round blue window is on cx in the upper third of the body; the flame is an orange teardrop with a smaller yellow one inside, starting at the bottom edge of the body. Fill the whole background dark blue first and draw the stars before the rocket.", | |
| "s09": "Space the lamps evenly inside the housing without overlap: for a housing from y=top to y=top+h, put the lamp centres at top+h/6, top+h/2 and top+5h/6, with radius about h/8. 'Dimmed' means a dark, desaturated colour (for example #5a4a00 for yellow and #0b4a1c for green), not the bright colour. Show the lit red lamp with a bright red and a glow: a larger circle behind it with a radial gradient from semi-transparent red to transparent (or an feGaussianBlur filter)." | |
| } | |