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

Libraries

How to use BenjaminHelle/LFM2-350M-code with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BenjaminHelle/LFM2-350M-code",
	filename="LFM2-350M.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use BenjaminHelle/LFM2-350M-code with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

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

LM Studio
Jan
Ollama
How to use BenjaminHelle/LFM2-350M-code with Ollama:
```
ollama run hf.co/BenjaminHelle/LFM2-350M-code:Q4_K_M
```

Unsloth Studio new

How to use BenjaminHelle/LFM2-350M-code with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for BenjaminHelle/LFM2-350M-code to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for BenjaminHelle/LFM2-350M-code to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BenjaminHelle/LFM2-350M-code to start chatting

Pi new

How to use BenjaminHelle/LFM2-350M-code with Pi:

Start the llama.cpp server

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

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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/LFM2-350M-code:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BenjaminHelle/LFM2-350M-code with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

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

Lemonade

How to use BenjaminHelle/LFM2-350M-code with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.LFM2-350M-code-Q4_K_M

List all available models

lemonade list

BenjaminHelle commited on Feb 27

Commit

909aedb

verified ·

1 Parent(s): 8cff4c0

Trained with Unsloth - config

Browse files

Files changed (1) hide show

config.json +57 -0

config.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+    "architectures": [
+        "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": true,
+    "block_dim": 1024,
+    "block_ff_dim": 6656,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_mlp_init_scale": 1.0,
+    "block_multiple_of": 256,
+    "block_norm_eps": 1e-05,
+    "block_out_init_scale": 1.0,
+    "block_use_swiglu": true,
+    "block_use_xavier_init": true,
+    "bos_token_id": 1,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 1024,
+    "conv_dim_out": 1024,
+    "conv_use_xavier_init": true,
+    "torch_dtype": "float16",
+    "eos_token_id": 7,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 6656,
+    "layer_types": [
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_heads": 16,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rope_theta": 1000000.0,
+    "unsloth_version": "2026.2.1",
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+}