Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

llama-swap
/
LFM3-1.7B-HelpAgent

Text Generation
Transformers
ONNX
Safetensors
GGUF
Transformers.js
English
lfm3
llama-swap
webgpu
fine-tuned
tool-calling
custom_code
conversational
Model card Files Files and versions
xet
Community

Instructions to use llama-swap/LFM3-1.7B-HelpAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use llama-swap/LFM3-1.7B-HelpAgent with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="llama-swap/LFM3-1.7B-HelpAgent", trust_remote_code=True)
    messages = [
        {"role": "user", "content": "Who are you?"},
    ]
    pipe(messages)
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForCausalLM
    
    tokenizer = AutoTokenizer.from_pretrained("llama-swap/LFM3-1.7B-HelpAgent", trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained("llama-swap/LFM3-1.7B-HelpAgent", trust_remote_code=True, device_map="auto")
    messages = [
        {"role": "user", "content": "Who are you?"},
    ]
    inputs = tokenizer.apply_chat_template(
    	messages,
    	add_generation_prompt=True,
    	tokenize=True,
    	return_dict=True,
    	return_tensors="pt",
    ).to(model.device)
    
    outputs = model.generate(**inputs, max_new_tokens=256)
    print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
  • Transformers.js

    How to use llama-swap/LFM3-1.7B-HelpAgent with Transformers.js:

    // npm i @huggingface/transformers
    import { pipeline } from '@huggingface/transformers';
    
    // Allocate pipeline
    const pipe = await pipeline('text-generation', 'llama-swap/LFM3-1.7B-HelpAgent');
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • llama.cpp

    How to use llama-swap/LFM3-1.7B-HelpAgent 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 llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    # Run inference directly in the terminal:
    llama cli -hf llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    Install from WinGet (Windows)
    winget install llama.cpp
    # Start a local OpenAI-compatible server with a web UI:
    llama serve -hf llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    # Run inference directly in the terminal:
    llama cli -hf llama-swap/LFM3-1.7B-HelpAgent:Q4_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 llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    # Run inference directly in the terminal:
    ./build/bin/llama cli -hf llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    Use Docker
    docker model run hf.co/llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
  • Llama new
  • LM Studio
  • Jan
  • vLLM

    How to use llama-swap/LFM3-1.7B-HelpAgent with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "llama-swap/LFM3-1.7B-HelpAgent"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "llama-swap/LFM3-1.7B-HelpAgent",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
    Use Docker
    docker model run hf.co/llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
  • SGLang

    How to use llama-swap/LFM3-1.7B-HelpAgent with SGLang:

    Install from pip and serve model
    # Install SGLang from pip:
    pip install sglang
    # Start the SGLang server:
    python3 -m sglang.launch_server \
        --model-path "llama-swap/LFM3-1.7B-HelpAgent" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "llama-swap/LFM3-1.7B-HelpAgent",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
    Use Docker images
    docker run --gpus all \
        --shm-size 32g \
        -p 30000:30000 \
        -v ~/.cache/huggingface:/root/.cache/huggingface \
        --env "HF_TOKEN=<secret>" \
        --ipc=host \
        lmsysorg/sglang:latest \
        python3 -m sglang.launch_server \
            --model-path "llama-swap/LFM3-1.7B-HelpAgent" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "llama-swap/LFM3-1.7B-HelpAgent",
    		"messages": [
    			{
    				"role": "user",
    				"content": "What is the capital of France?"
    			}
    		]
    	}'
  • Ollama

    How to use llama-swap/LFM3-1.7B-HelpAgent with Ollama:

    ollama run hf.co/llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
  • Unsloth Desktop
  • Pi

    How to use llama-swap/LFM3-1.7B-HelpAgent with Pi:

    Start the llama.cpp server
    # Install llama.cpp:
    brew install llama.cpp
    # Start a local OpenAI-compatible server:
    llama serve -hf llama-swap/LFM3-1.7B-HelpAgent: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:9931/v1",
          "api": "openai-completions",
          "apiKey": "none",
          "models": [
            {
              "id": "llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M"
            }
          ]
        }
      }
    }
    Run Pi
    # Start Pi in your project directory:
    pi
  • Docker Model Runner

    How to use llama-swap/LFM3-1.7B-HelpAgent with Docker Model Runner:

    docker model run hf.co/llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
  • Lemonade

    How to use llama-swap/LFM3-1.7B-HelpAgent with Lemonade:

    Pull the model
    # Download Lemonade from https://lemonade-server.ai/
    lemonade pull llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    Run and chat with the model
    lemonade run user.LFM3-1.7B-HelpAgent-Q4_K_M
    List all available models
    lemonade list
  • Hermes Agent

    How to use llama-swap/LFM3-1.7B-HelpAgent with Hermes Agent:

    Start the llama.cpp server
    # Install llama.cpp:
    brew install llama.cpp
    # Start a local OpenAI-compatible server:
    llama serve -hf llama-swap/LFM3-1.7B-HelpAgent: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://127.0.0.1:9931/v1
    hermes config set model.default llama-swap/LFM3-1.7B-HelpAgent:Q4_K_M
    Run Hermes
    hermes
  • Atomic Chat
  • OpenClaw

    How to use llama-swap/LFM3-1.7B-HelpAgent with OpenClaw:

    Start the llama.cpp server
    # Install llama.cpp:
    brew install llama.cpp
    # Start a local OpenAI-compatible server:
    llama serve -hf llama-swap/LFM3-1.7B-HelpAgent: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://127.0.0.1:9931/v1 \
      --custom-model-id "llama-swap/LFM3-1.7B-HelpAgent: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"
LFM3-1.7B-HelpAgent
7.58 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
mostlygeek's picture
mostlygeek
Add q4f16 and q4 ONNX models for Transformers.js and WebGPU
0898fda verified 15 days ago
  • onnx
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago
  • .gitattributes
    1.76 kB
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago
  • LFM3-1.7B-HelpAgent-Q4_K_M.gguf
    1.1 GB
    xet
    Set the GGUF's general.name to LFM3-1.7B-HelpAgent 15 days ago
  • LICENSE
    10.6 kB
    Add LFM3-1.7B-HelpAgent 15 days ago
  • NOTICE
    1.56 kB
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago
  • README.md
    10.2 kB
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago
  • chat_template.jinja
    12.1 kB
    Add LFM3-1.7B-HelpAgent 15 days ago
  • config.json
    1.66 kB
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago
  • configuration_lfm3.py
    6.11 kB
    Add LFM3-1.7B-HelpAgent 15 days ago
  • generation_config.json
    328 Bytes
    Add LFM3-1.7B-HelpAgent 15 days ago
  • lfm3_conv.py
    8.53 kB
    Add LFM3-1.7B-HelpAgent 15 days ago
  • model.safetensors
    3.46 GB
    xet
    Add LFM3-1.7B-HelpAgent 15 days ago
  • modeling_lfm3.py
    42.4 kB
    Add LFM3-1.7B-HelpAgent 15 days ago
  • special_tokens_map.json
    92 Bytes
    Add LFM3-1.7B-HelpAgent 15 days ago
  • tokenizer.json
    17.9 MB
    xet
    Add LFM3-1.7B-HelpAgent 15 days ago
  • tokenizer_config.json
    14.3 kB
    Add q4f16 and q4 ONNX models for Transformers.js and WebGPU 15 days ago