Image-Text-to-Text
MLX
Safetensors
Transformers
llava_qwen2
text-generation
conversational
custom_code
4-bit precision
Instructions to use EZCon/FastVLM-1.5B-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use EZCon/FastVLM-1.5B-4bit-mlx 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("EZCon/FastVLM-1.5B-4bit-mlx") config = load_config("EZCon/FastVLM-1.5B-4bit-mlx") # 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) - Transformers
How to use EZCon/FastVLM-1.5B-4bit-mlx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="EZCon/FastVLM-1.5B-4bit-mlx", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("EZCon/FastVLM-1.5B-4bit-mlx", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use EZCon/FastVLM-1.5B-4bit-mlx with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EZCon/FastVLM-1.5B-4bit-mlx" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EZCon/FastVLM-1.5B-4bit-mlx", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/EZCon/FastVLM-1.5B-4bit-mlx
- SGLang
How to use EZCon/FastVLM-1.5B-4bit-mlx 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 "EZCon/FastVLM-1.5B-4bit-mlx" \ --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": "EZCon/FastVLM-1.5B-4bit-mlx", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "EZCon/FastVLM-1.5B-4bit-mlx" \ --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": "EZCon/FastVLM-1.5B-4bit-mlx", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use EZCon/FastVLM-1.5B-4bit-mlx with Docker Model Runner:
docker model run hf.co/EZCon/FastVLM-1.5B-4bit-mlx
| { | |
| "architectures": [ | |
| "LlavaQwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "llava_qwen.LlavaConfig", | |
| "AutoModelForCausalLM": "llava_qwen.LlavaQwen2ForCausalLM" | |
| }, | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": 151645, | |
| "freeze_mm_mlp_adapter": false, | |
| "generation_config": { | |
| "do_sample": true, | |
| "temperature": null, | |
| "top_p": null, | |
| "transformers_version": "4.39.3" | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "image_aspect_ratio": "pad", | |
| "image_grid_pinpoints": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "mm_hidden_size": 3072, | |
| "mm_patch_merge_type": "flat", | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "mm_vision_tower": "mobileclip_l_1024", | |
| "model_type": "llava_qwen2", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "temperature": null, | |
| "tie_word_embeddings": true, | |
| "tokenizer_model_max_length": 8192, | |
| "tokenizer_padding_side": "right", | |
| "top_p": null, | |
| "transformers_version": "4.39.3", | |
| "tune_mm_mlp_adapter": false, | |
| "unfreeze_mm_vision_tower": true, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "use_sliding_window": false, | |
| "vision_config": {}, | |
| "vocab_size": 151936 | |
| } |