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

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

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"

LFM3-1.7B-inference-modules-experiments / research /scripts /cmp.py

HelioAI

LFM3-1.7B inference modules: experimental release

67ebcef verified 2 days ago

Raw History Blame Contribute Delete

1.41 kB

"""Compare two graded runs over the same items: per-task accuracy (mean over samples), item-level paired difference
with a bootstrap 95% CI, plus mean generated tokens.  usage: cmp.py <tagA> <tagB> [--file graded.jsonl]"""
import collections
import json
import random
import sys


def load(tag):
    d = collections.defaultdict(list)
    for g in map(json.loads, open(f"results/{tag}/graded.jsonl", encoding="utf-8")):
        t = "code" if g["task"].startswith("code") else g["task"]
        d[(t, g["id"])].append((g["correct"], g["n_tokens"]))
    return d


a, b = load(sys.argv[1]), load(sys.argv[2])
keys = [k for k in a if k in b]
rng = random.Random(0)
for task in sorted({k[0] for k in keys}) + ["ALL"]:
    ks = [k for k in keys if task in ("ALL", k[0])]
    da = [sum(c for c, _ in a[k]) / len(a[k]) for k in ks]
    db = [sum(c for c, _ in b[k]) / len(b[k]) for k in ks]
    diff = [y - x for x, y in zip(da, db)]
    boots = sorted(sum(rng.choice(diff) for _ in diff) / len(diff) for _ in range(2000))
    ta = sum(n for k in ks for _, n in a[k]) / sum(len(a[k]) for k in ks)
    tb = sum(n for k in ks for _, n in b[k]) / sum(len(b[k]) for k in ks)
    print(f"{task:8s} n={len(ks):3d}  {100 * sum(da) / len(ks):5.1f} -> {100 * sum(db) / len(ks):5.1f}  "
          f"d={100 * sum(diff) / len(ks):+5.1f} [{100 * boots[50]:+.1f}, {100 * boots[1949]:+.1f}]  "
          f"tok {ta:.0f} -> {tb:.0f}")

	"""Compare two graded runs over the same items: per-task accuracy (mean over samples), item-level paired difference
	with a bootstrap 95% CI, plus mean generated tokens. usage: cmp.py <tagA> <tagB> [--file graded.jsonl]"""
	import collections
	import json
	import random
	import sys


	def load(tag):
	d = collections.defaultdict(list)
	for g in map(json.loads, open(f"results/{tag}/graded.jsonl", encoding="utf-8")):
	t = "code" if g["task"].startswith("code") else g["task"]
	d[(t, g["id"])].append((g["correct"], g["n_tokens"]))
	return d


	a, b = load(sys.argv[1]), load(sys.argv[2])
	keys = [k for k in a if k in b]
	rng = random.Random(0)
	for task in sorted({k[0] for k in keys}) + ["ALL"]:
	ks = [k for k in keys if task in ("ALL", k[0])]
	da = [sum(c for c, _ in a[k]) / len(a[k]) for k in ks]
	db = [sum(c for c, _ in b[k]) / len(b[k]) for k in ks]
	diff = [y - x for x, y in zip(da, db)]
	boots = sorted(sum(rng.choice(diff) for _ in diff) / len(diff) for _ in range(2000))
	ta = sum(n for k in ks for _, n in a[k]) / sum(len(a[k]) for k in ks)
	tb = sum(n for k in ks for _, n in b[k]) / sum(len(b[k]) for k in ks)
	print(f"{task:8s} n={len(ks):3d} {100 * sum(da) / len(ks):5.1f} -> {100 * sum(db) / len(ks):5.1f} "
	f"d={100 * sum(diff) / len(ks):+5.1f} [{100 * boots[50]:+.1f}, {100 * boots[1949]:+.1f}] "
	f"tok {ta:.0f} -> {tb:.0f}")