Instructions to use BenjaminHelle/LFM2.5-350M-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use BenjaminHelle/LFM2.5-350M-coder 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 BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Use Docker

docker model run hf.co/BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

LM Studio
Jan

vLLM

How to use BenjaminHelle/LFM2.5-350M-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BenjaminHelle/LFM2.5-350M-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BenjaminHelle/LFM2.5-350M-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Ollama
How to use BenjaminHelle/LFM2.5-350M-coder with Ollama:
```
ollama run hf.co/BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
```
Unsloth Desktop

How to use BenjaminHelle/LFM2.5-350M-coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BenjaminHelle/LFM2.5-350M-coder:Q4_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": "BenjaminHelle/LFM2.5-350M-coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BenjaminHelle/LFM2.5-350M-coder with Docker Model Runner:
```
docker model run hf.co/BenjaminHelle/LFM2.5-350M-coder:Q4_K_M
```

Lemonade

How to use BenjaminHelle/LFM2.5-350M-coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-350M-coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use BenjaminHelle/LFM2.5-350M-coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BenjaminHelle/LFM2.5-350M-coder:Q4_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 BenjaminHelle/LFM2.5-350M-coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BenjaminHelle/LFM2.5-350M-coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BenjaminHelle/LFM2.5-350M-coder:Q4_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 "BenjaminHelle/LFM2.5-350M-coder:Q4_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"

BenjaminHelle commited on Jul 9

Commit

aa130a4

verified ·

1 Parent(s): 780095c

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -3,12 +3,17 @@ tags:
 - gguf
 - llama.cpp
 - unsloth
 ---
 # LFM2.5-350M-coder : GGUF
 This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
 **Example usage**:
 - For text only LLMs:    `llama-cli -hf BenjaminHelle/LFM2.5-350M-coder --jinja`
@@ -18,4 +23,4 @@ This model was finetuned and converted to GGUF format using [Unsloth](https://gi
 - `LFM2.5-350M.Q8_0.gguf`
 - `LFM2.5-350M.Q4_K_M.gguf`
 This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - gguf
 - llama.cpp
 - unsloth
+- code
+datasets:
+- nickrosh/Evol-Instruct-Code-80k-v1
+base_model:
+- LiquidAI/LFM2.5-350M
 ---
 # LFM2.5-350M-coder : GGUF
 This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+Dataset used: https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1
 **Example usage**:
 - For text only LLMs:    `llama-cli -hf BenjaminHelle/LFM2.5-350M-coder --jinja`
 - `LFM2.5-350M.Q8_0.gguf`
 - `LFM2.5-350M.Q4_K_M.gguf`
 This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)