Instructions to use harrier77/LFM2.5-1.2B-ITA-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use harrier77/LFM2.5-1.2B-ITA-GGUF 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 harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_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 harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_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 harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M

Use Docker

docker model run hf.co/harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M

LM Studio
Jan
Ollama
How to use harrier77/LFM2.5-1.2B-ITA-GGUF with Ollama:
```
ollama run hf.co/harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
```
Unsloth Desktop

How to use harrier77/LFM2.5-1.2B-ITA-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf harrier77/LFM2.5-1.2B-ITA-GGUF: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": "harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use harrier77/LFM2.5-1.2B-ITA-GGUF with Docker Model Runner:
```
docker model run hf.co/harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M
```

Lemonade

How to use harrier77/LFM2.5-1.2B-ITA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.LFM2.5-1.2B-ITA-GGUF-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use harrier77/LFM2.5-1.2B-ITA-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf harrier77/LFM2.5-1.2B-ITA-GGUF: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 harrier77/LFM2.5-1.2B-ITA-GGUF:Q5_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use harrier77/LFM2.5-1.2B-ITA-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf harrier77/LFM2.5-1.2B-ITA-GGUF: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 "harrier77/LFM2.5-1.2B-ITA-GGUF: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"

LFM2.5-1.2B Italian

LiquidAI/LFM2.5-1.2B-Base model further continued-pretrained on Italian Wikipedia and then fine-tuned with Italian instructions (Alpaca format).

Training

Continued Pretraining: ~1% of Italian Wikipedia (20231101.it dump), texts ≥ 600 characters
Instruction Tuning: dataset DanielSc4/alpaca-cleaned-italian
Technique: LoRA + Unsloth (merged in full precision / fp16)
Original base model: multilingual, with significant improvement in Italian

Supported Languages

Improved in Italian.
Maintains performance in English and residual capability in the other languages of the base model.

This model follows the exact continued pretraining + instruction tuning recipe recently published by LiquidAI in their official cookbook: https://github.com/Liquid4All/cookbook/blob/main/finetuning/notebooks/cpt_translation_with_unsloth.ipynb I only replaced Korean with Italian by using: Italian Wikipedia (20231101.it dump) instead of Korean Wikipedia for continued pretraining DanielSc4/alpaca-cleaned-italian dataset instead of the Korean Alpaca version for instruction tuning All other steps (LoRA including embed_tokens & lm_head, separate embedding learning rate, Unsloth, fp16 merge) are identical to the original notebook.

Downloads last month: 17

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

harrier77
/

LFM2.5-1.2B-ITA-GGUF

LFM2.5-1.2B Italian

Training

Supported Languages

Datasets used to train harrier77/LFM2.5-1.2B-ITA-GGUF