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 /agg_eval.py

HelioAI

LFM3-1.7B inference modules: experimental release

67ebcef verified 2 days ago

Raw History Blame Contribute Delete

1.96 kB

"""Compares the self-aggregation module with the weighted vote over the same K attempts.
Split problems (attempts disagree) get the aggregator's answer, unanimous ones keep the shared answer.
usage: agg_eval.py data/agg/m180.jsonl agg_m180_dm   (the second argument is a graded results tag)"""
import collections
import json
import os
import random
import sys

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from grade import grade_math  # noqa: E402

items = {json.loads(l)["id"]: json.loads(l) for l in open(sys.argv[1], encoding="utf-8")}
agg = collections.defaultdict(list)
for l in open(os.path.join("results", sys.argv[2], "graded.jsonl"), encoding="utf-8"):
    g = json.loads(l)
    agg[g["id"]].append(g["correct"])


def vote_ok(it):
    v = it["vote"]
    if v is None:
        return False
    return v == it["answer"] if it["task"] == "mmlupro" else bool(grade_math("\\boxed{" + v + "}", it["answer"]))


vote = {i: vote_ok(it) for i, it in items.items()}
split = [i for i, it in items.items() if not it["unanimous"] and i in agg]
diff = [sum(agg[i]) / len(agg[i]) - vote[i] for i in split]
rng = random.Random(0)
boots = sorted(sum(rng.choice(diff) for _ in diff) / len(diff) for _ in range(2000)) if diff else [0] * 2000
n = len(items)
hyb = sum(vote[i] for i, it in items.items() if it["unanimous"] or i not in agg) + sum(sum(agg[i]) / len(agg[i]) for i in split)
print(f"{sys.argv[2]}: {n} problems, {len(split)} split, samples/problem {sum(len(agg[i]) for i in split) / max(len(split), 1):.1f}")
print(f"  split problems: vote {100 * sum(vote[i] for i in split) / max(len(split), 1):.1f} -> aggregator "
      f"{100 * sum(sum(agg[i]) / len(agg[i]) for i in split) / max(len(split), 1):.1f}")
print(f"  all problems:   vote {100 * sum(vote.values()) / n:.1f} -> vote+aggregator {100 * hyb / n:.1f}  "
      f"d={100 * sum(diff) / n:+.1f} [{100 * boots[50] * len(split) / n:+.1f}, {100 * boots[1949] * len(split) / n:+.1f}]")

	"""Compares the self-aggregation module with the weighted vote over the same K attempts.
	Split problems (attempts disagree) get the aggregator's answer, unanimous ones keep the shared answer.
	usage: agg_eval.py data/agg/m180.jsonl agg_m180_dm (the second argument is a graded results tag)"""
	import collections
	import json
	import os
	import random
	import sys

	sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
	from grade import grade_math # noqa: E402

	items = {json.loads(l)["id"]: json.loads(l) for l in open(sys.argv[1], encoding="utf-8")}
	agg = collections.defaultdict(list)
	for l in open(os.path.join("results", sys.argv[2], "graded.jsonl"), encoding="utf-8"):
	g = json.loads(l)
	agg[g["id"]].append(g["correct"])


	def vote_ok(it):
	v = it["vote"]
	if v is None:
	return False
	return v == it["answer"] if it["task"] == "mmlupro" else bool(grade_math("\\boxed{" + v + "}", it["answer"]))


	vote = {i: vote_ok(it) for i, it in items.items()}
	split = [i for i, it in items.items() if not it["unanimous"] and i in agg]
	diff = [sum(agg[i]) / len(agg[i]) - vote[i] for i in split]
	rng = random.Random(0)
	boots = sorted(sum(rng.choice(diff) for _ in diff) / len(diff) for _ in range(2000)) if diff else [0] * 2000
	n = len(items)
	hyb = sum(vote[i] for i, it in items.items() if it["unanimous"] or i not in agg) + sum(sum(agg[i]) / len(agg[i]) for i in split)
	print(f"{sys.argv[2]}: {n} problems, {len(split)} split, samples/problem {sum(len(agg[i]) for i in split) / max(len(split), 1):.1f}")
	print(f" split problems: vote {100 * sum(vote[i] for i in split) / max(len(split), 1):.1f} -> aggregator "
	f"{100 * sum(sum(agg[i]) / len(agg[i]) for i in split) / max(len(split), 1):.1f}")
	print(f" all problems: vote {100 * sum(vote.values()) / n:.1f} -> vote+aggregator {100 * hyb / n:.1f} "
	f"d={100 * sum(diff) / n:+.1f} [{100 * boots[50] * len(split) / n:+.1f}, {100 * boots[1949] * len(split) / n:+.1f}]")