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/scripts/mentor_sheet.py from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 2.59 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/scripts/mentor_sheet.py
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/research/scripts/mentor_sheet.py
-
curl -L -o mentor_sheet.py https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/scripts/mentor_sheet.py
2.59 kB
| """Review sheets for the mentor: per task one row with the student's attempts side by side and the browser report. | |
| usage: mentor_sheet.py --tag mtr_dm --tasks data/visual/mentor_tasks.jsonl --out results/mentor/review --per 5 | |
| Rows: '<id> <first words of the task>' and under each screenshot 'ok' or the problems found (blank, errors, static). | |
| """ | |
| import argparse | |
| import json | |
| import os | |
| from PIL import Image, ImageDraw | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--tag", required=True) | |
| ap.add_argument("--tasks", default="data/visual/mentor_tasks.jsonl") | |
| ap.add_argument("--out", required=True) | |
| ap.add_argument("--per", type=int, default=5) | |
| ap.add_argument("--samples", type=int, default=2) | |
| ap.add_argument("--ids", nargs="*") | |
| ap.add_argument("--w", type=int, default=400) | |
| a = ap.parse_args() | |
| tasks = [json.loads(l) for l in open(a.tasks, encoding="utf-8")] | |
| if a.ids: | |
| tasks = [t for t in tasks if t["id"].split("/")[-1] in a.ids] | |
| rep = {} | |
| for r in json.load(open(os.path.join("results", a.tag, "visual.json"))): | |
| rep[(r["id"].split("/")[-1], r["sample"])] = r | |
| def flags(r, task): | |
| if r is None: | |
| return "no answer" | |
| out = [] | |
| if r.get("parse_error"): | |
| out.append("bad XML") | |
| if r["errors"]: | |
| out.append("JS: " + r["errors"][0][:60]) | |
| if r["failed"]: | |
| out.append("load failed") | |
| if r["blank"]: | |
| out.append("blank") | |
| if task["animated"] and not r["animated"] and not r["blank"]: | |
| out.append("static") | |
| return "ok" if not out else "; ".join(out) | |
| os.makedirs(a.out, exist_ok=True) | |
| w, h, head, foot = a.w, a.w * 3 // 4, 20, 18 | |
| for k in range(0, len(tasks), a.per): | |
| rows = tasks[k:k + a.per] | |
| sheet = Image.new("RGB", (a.samples * (w + 6) + 6, len(rows) * (h + head + foot + 8) + 6), "#202124") | |
| d = ImageDraw.Draw(sheet) | |
| for i, t in enumerate(rows): | |
| tid = t["id"].split("/")[-1] | |
| y = 6 + i * (h + head + foot + 8) | |
| d.text((8, y + 3), f"{tid} {t['prompt'][:95]}", fill="#e8eaed") | |
| for s in range(a.samples): | |
| x = 6 + s * (w + 6) | |
| p = os.path.join("results", a.tag, "png", f"{tid}_{s}.png") | |
| if os.path.exists(p): | |
| sheet.paste(Image.open(p).convert("RGB").resize((w, h)), (x, y + head)) | |
| else: | |
| d.rectangle([x, y + head, x + w, y + head + h], outline="#5f6368") | |
| d.text((x + 2, y + head + h + 3), f"s{s}: {flags(rep.get((tid, s)), t)}", fill="#fdd663") | |
| sheet.save(os.path.join(a.out, f"sheet_{k // a.per:02d}.png")) | |
| print(f"{(len(tasks) + a.per - 1) // a.per} sheets in {a.out}") | |