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 /extrap.py

HelioAI

LFM3-1.7B inference modules: experimental release

67ebcef verified 2 days ago

Raw History Blame Contribute Delete

1.33 kB

"""Extrapolate along the update an RL step made: theta = theta_new + beta * (theta_new - theta_old).
The delta is computed in fp32 per tensor; non-weight files are copied from <new>.
usage: extrap.py <new_dir> <old_dir> <beta> <out_dir>"""
import glob, os, shutil, sys, torch
from safetensors.torch import load_file, save_file
new_dir, old_dir, beta, out = sys.argv[1], sys.argv[2], float(sys.argv[3]), sys.argv[4]


def load_all(d):
    sd = {}
    for f in sorted(glob.glob(os.path.join(d, "*.safetensors"))):
        sd.update(load_file(f))
    return sd


new, old = load_all(new_dir), load_all(old_dir)
res, rel = {}, []
for k, v in new.items():
    o = old.get(k)
    if o is None or o.shape != v.shape:
        res[k] = v
        continue
    d = v.float() - o.float()
    res[k] = (v.float() + beta * d).to(v.dtype)
    if d.abs().sum() > 0:
        rel.append(d.norm().item() / o.float().norm().item())
os.makedirs(out, exist_ok=True)
save_file(res, os.path.join(out, "model.safetensors"), metadata={"format": "pt"})
for f in os.listdir(new_dir):
    p = os.path.join(new_dir, f)
    if os.path.isfile(p) and not f.endswith(".safetensors") and f != "model.safetensors.index.json":
        shutil.copy(p, out)
print(f"{len(rel)} tensors changed, mean relative update {sum(rel) / max(1, len(rel)):.2e}, beta {beta} -> {out}")

	"""Extrapolate along the update an RL step made: theta = theta_new + beta * (theta_new - theta_old).
	The delta is computed in fp32 per tensor; non-weight files are copied from <new>.
	usage: extrap.py <new_dir> <old_dir> <beta> <out_dir>"""
	import glob, os, shutil, sys, torch
	from safetensors.torch import load_file, save_file
	new_dir, old_dir, beta, out = sys.argv[1], sys.argv[2], float(sys.argv[3]), sys.argv[4]


	def load_all(d):
	sd = {}
	for f in sorted(glob.glob(os.path.join(d, "*.safetensors"))):
	sd.update(load_file(f))
	return sd


	new, old = load_all(new_dir), load_all(old_dir)
	res, rel = {}, []
	for k, v in new.items():
	o = old.get(k)
	if o is None or o.shape != v.shape:
	res[k] = v
	continue
	d = v.float() - o.float()
	res[k] = (v.float() + beta * d).to(v.dtype)
	if d.abs().sum() > 0:
	rel.append(d.norm().item() / o.float().norm().item())
	os.makedirs(out, exist_ok=True)
	save_file(res, os.path.join(out, "model.safetensors"), metadata={"format": "pt"})
	for f in os.listdir(new_dir):
	p = os.path.join(new_dir, f)
	if os.path.isfile(p) and not f.endswith(".safetensors") and f != "model.safetensors.index.json":
	shutil.copy(p, out)
	print(f"{len(rel)} tensors changed, mean relative update {sum(rel) / max(1, len(rel)):.2e}, beta {beta} -> {out}")