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/prep_lcb.py from HelioAI/LFM3-1.7B-inference-modules-experiments: direct link, hf CLI and curl.
- Browser
- Download file 2.44 kB
-
https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/scripts/prep_lcb.py
- Command line
-
hf download hf://HelioAI/LFM3-1.7B-inference-modules-experiments/research/scripts/prep_lcb.py
-
curl -L -o prep_lcb.py https://huggingface.co/HelioAI/LFM3-1.7B-inference-modules-experiments/resolve/main/research/scripts/prep_lcb.py
2.44 kB
| """Converts LiveCodeBench code_generation_lite (test6.jsonl, problems from 2025) into eval items. | |
| Hidden tests are stored pickled+zlib+base64 in the source; they are decoded with a restricted unpickler that refuses | |
| every global (only plain str/list/dict data can load), so the file cannot execute code. | |
| item: {id, task: "lcb", testtype: stdin|functional, prompt, func_name, public: [[in,out]], hidden: [[in,out]]} | |
| usage: python -I prep_lcb.py <raw test6.jsonl> <out items.jsonl> | |
| """ | |
| import base64 | |
| import io | |
| import json | |
| import pickle | |
| import sys | |
| import zlib | |
| class SafeUnpickler(pickle.Unpickler): | |
| def find_class(self, module, name): | |
| raise pickle.UnpicklingError(f"global {module}.{name} refused") | |
| def decode_private(s): | |
| try: | |
| return json.loads(s) | |
| except Exception: | |
| raw = zlib.decompress(base64.b64decode(s.encode("utf-8"))) | |
| return json.loads(SafeUnpickler(io.BytesIO(raw)).load()) | |
| STDIN_TAIL = ("\n\nWrite a Python 3 program that reads from standard input and writes to standard output. " | |
| "Put the complete program in a single ```python code block.") | |
| FUNC_TAIL = ("\n\nComplete the following starter code and return the full solution (the class with the method) " | |
| "in a single ```python code block.\n\n```python\n{starter}\n```") | |
| src, dst = sys.argv[1], sys.argv[2] | |
| n = 0 | |
| with open(src, encoding="utf-8") as f, open(dst, "w", encoding="utf-8") as out: | |
| for line in f: | |
| r = json.loads(line) | |
| pub = json.loads(r["public_test_cases"]) | |
| hid = decode_private(r["private_test_cases"]) | |
| ttype = pub[0]["testtype"] if pub else hid[0]["testtype"] | |
| meta = json.loads(r.get("metadata") or "{}") | |
| starter = r.get("starter_code") or "" | |
| prompt = r["question_content"].strip() + (FUNC_TAIL.format(starter=starter.strip()) if ttype == "functional" | |
| else STDIN_TAIL) | |
| out.write(json.dumps({"id": f"lcb/{r['question_id']}", "task": "lcb", "testtype": ttype, | |
| "difficulty": r.get("difficulty"), "date": r.get("contest_date"), | |
| "func_name": meta.get("func_name"), "prompt": prompt, | |
| "public": [[t["input"], t["output"]] for t in pub], | |
| "hidden": [[t["input"], t["output"]] for t in pub + hid]}, ensure_ascii=False) + "\n") | |
| n += 1 | |
| print(n, "problems") | |