Image-Text-to-Text
MLX
Safetensors
lfm2-vl
liquid
lfm2.5-vl
lfm2.5
edge
conversational
8-bit precision
Instructions to use LiquidAI/LFM2.5-VL-450M-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use LiquidAI/LFM2.5-VL-450M-MLX-8bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("LiquidAI/LFM2.5-VL-450M-MLX-8bit") config = load_config("LiquidAI/LFM2.5-VL-450M-MLX-8bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Pi
How to use LiquidAI/LFM2.5-VL-450M-MLX-8bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "LiquidAI/LFM2.5-VL-450M-MLX-8bit"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "LiquidAI/LFM2.5-VL-450M-MLX-8bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use LiquidAI/LFM2.5-VL-450M-MLX-8bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "LiquidAI/LFM2.5-VL-450M-MLX-8bit"
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 LiquidAI/LFM2.5-VL-450M-MLX-8bit
Run Hermes
hermes
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -80,7 +80,6 @@ result = generate(
|
|
| 80 |
processor,
|
| 81 |
prompt,
|
| 82 |
[image],
|
| 83 |
-
max_tokens=256,
|
| 84 |
temp=0.1,
|
| 85 |
min_p=0.15,
|
| 86 |
repetition_penalty=1.05,
|
|
@@ -96,7 +95,6 @@ print(result.text)
|
|
| 96 |
| temperature | 0.1 |
|
| 97 |
| min_p | 0.15 |
|
| 98 |
| repetition_penalty | 1.05 |
|
| 99 |
-
| max_tokens | 256 |
|
| 100 |
|
| 101 |
## License
|
| 102 |
|
|
|
|
| 80 |
processor,
|
| 81 |
prompt,
|
| 82 |
[image],
|
|
|
|
| 83 |
temp=0.1,
|
| 84 |
min_p=0.15,
|
| 85 |
repetition_penalty=1.05,
|
|
|
|
| 95 |
| temperature | 0.1 |
|
| 96 |
| min_p | 0.15 |
|
| 97 |
| repetition_penalty | 1.05 |
|
|
|
|
| 98 |
|
| 99 |
## License
|
| 100 |
|