Text Generation
Safetensors
GGUF
llama-cpp
abliterated
uncensored
lfm2
lfm2.5
liquid
edge
refusal-ablation
conversational
Instructions to use AdminHugging/LFM2.5-1.2B-Instruct-hehe 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 AdminHugging/LFM2.5-1.2B-Instruct-hehe 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 AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0 # Run inference directly in the terminal: llama cli -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0 # Run inference directly in the terminal: llama cli -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
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 AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
Use Docker
docker model run hf.co/AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdminHugging/LFM2.5-1.2B-Instruct-hehe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/LFM2.5-1.2B-Instruct-hehe", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
- Ollama
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with Ollama:
ollama run hf.co/AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
- Unsloth Desktop
- Pi
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with Docker Model Runner:
docker model run hf.co/AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
- Lemonade
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
Run and chat with the model
lemonade run user.LFM2.5-1.2B-Instruct-hehe-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
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://127.0.0.1:9931/v1 hermes config set model.default AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AdminHugging/LFM2.5-1.2B-Instruct-hehe with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0
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://127.0.0.1:9931/v1 \ --custom-model-id "AdminHugging/LFM2.5-1.2B-Instruct-hehe:Q8_0" \ --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"
Commit History
-
GGUF-first model card: drop library_name, document bf16/ subfolder
Verified signature824e952 -
Move bf16 transformers build into bf16/ so the GGUF table renders at repo root
Verified signature66e7ca0 -
Add explicit Q8_0 download section
Verified signatureb2b3574 -
Add LFM2.5-1.2B-abliterated-Q8_0.gguf
Verified signature9b9f51d -
Add model.safetensors
Verified signatureb66ba07 -
Add LICENSE
Verified signature3769123 -
Add chat_template.jinja
Verified signaturecfddb8d -
Add special_tokens_map.json
Verified signature93a4000 -
Add tokenizer.json
Verified signatureb82154a -
Add tokenizer_config.json
Verified signature6360c05 -
Add generation_config.json
Verified signature3c49983 -
Add config.json
Verified signature6287351 -
Add abliteration_config.json
Verified signatureca1d313 -
Add README.md
Verified signaturecfe8147 -
Update LICENSE
Verified signatureda0d714 -
initial commit
Verified signaturebe4de64