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/tasks_fresh2.jsonl from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 4.31 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/tasks_fresh2.jsonl
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/research/data/visual/tasks_fresh2.jsonl
-
curl -L -o tasks_fresh2.jsonl https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/data/visual/tasks_fresh2.jsonl
4.31 kB
| {"id": "fresh2/s1", "task": "visual", "cat": "svg", "kind": "svg", "animated": false, "prompt": "Draw a cartoon hedgehog walking on grass: a brown spiky back made of many small triangles, a light brown face with a black nose and a black eye, small feet, and green grass along the bottom.\n\nAnswer with one complete SVG document (with xmlns and a viewBox) in a single ```svg code block. Do not use external images or fonts."} | |
| {"id": "fresh2/s2", "task": "visual", "cat": "svg", "kind": "svg", "animated": false, "prompt": "Draw a weather card: a rounded white card with the city 'Oslo', the temperature '18 °C' in large text, an icon of a sun partly behind a cloud, and three small labelled bars for wind, rain and humidity.\n\nAnswer with one complete SVG document (with xmlns and a viewBox) in a single ```svg code block. Do not use external images or fonts."} | |
| {"id": "fresh2/p1", "task": "visual", "cat": "html", "kind": "html", "animated": false, "prompt": "Build a 'Book a table' page for a restaurant called 'Olive & Thyme': a heading, a short welcome text, a reservation form (date, time, number of guests, name, phone, book button) and a side box with opening hours and the address.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Do not use external libraries."} | |
| {"id": "fresh2/p2", "task": "visual", "cat": "html", "kind": "html", "animated": false, "prompt": "Build a service status page: a header with the product name and an 'All systems operational' banner, a list of five services each with a green, yellow or red status pill, and an incident history of three past incidents with dates.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Do not use external libraries."} | |
| {"id": "fresh2/a1", "task": "visual", "cat": "canvas", "kind": "html", "animated": true, "prompt": "Make a bubble-popping game on a canvas: colourful bubbles float up from the bottom at different speeds; clicking a bubble pops it with a small burst of particles and adds one point to the score shown at the top.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Do not use external libraries."} | |
| {"id": "fresh2/a2", "task": "visual", "cat": "canvas", "kind": "html", "animated": true, "prompt": "Make an audio equalizer animation on a canvas: 24 vertical bars that rise and fall smoothly to a fake rhythm, each bar coloured from green at the bottom through yellow to red at the top, with small peak markers that fall slowly.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Do not use external libraries."} | |
| {"id": "fresh2/d1", "task": "visual", "cat": "three", "kind": "html", "animated": true, "prompt": "Make a three.js garden: a wooden bench made of boxes, a round pond (a flat blue cylinder), and five flowers (green stems with coloured petal spheres) on a grass ground, with the camera slowly circling.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Use three.js through this 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> and a <script type=\"module\">."} | |
| {"id": "fresh2/d2", "task": "visual", "cat": "three", "kind": "html", "animated": true, "prompt": "Make a three.js rocket launch: a rocket built from a white cylinder, a red cone nose and three fins standing on a grey launch pad, slowly rising with a flickering orange flame under it and grey smoke particles.\n\nAnswer with one complete, self-contained HTML file in a single ```html code block. Put CSS and JavaScript inline. Do not use external images. Use three.js through this 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> and a <script type=\"module\">."} | |