Instructions to use xcodemind/UICoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xcodemind/UICoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="xcodemind/UICoder")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("xcodemind/UICoder") model = AutoModelForImageTextToText.from_pretrained("xcodemind/UICoder") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use xcodemind/UICoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xcodemind/UICoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xcodemind/UICoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/xcodemind/UICoder
- SGLang
How to use xcodemind/UICoder 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 "xcodemind/UICoder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xcodemind/UICoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "xcodemind/UICoder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xcodemind/UICoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use xcodemind/UICoder with Docker Model Runner:
docker model run hf.co/xcodemind/UICoder
| { | |
| "_name_or_path": "/data02/users/lz/code/UICoder/checkpoints/stage0/l2048_p1024_vu_3m*3/checkpoint-90000", | |
| "architectures": [ | |
| "Pix2StructForConditionalGeneration" | |
| ], | |
| "decoder_start_token_id": 0, | |
| "eos_token_id": 1, | |
| "bos_token_id": 2, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": true, | |
| "is_vqa": false, | |
| "model_type": "pix2struct", | |
| "pad_token_id": 0, | |
| "text_config": { | |
| "d_ff": 3968, | |
| "encoder_hidden_size": 1536, | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "model_type": "pix2struct_text_model", | |
| "num_heads": 24, | |
| "num_layers": 18, | |
| "vocab_size": 50344 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "vision_config": { | |
| "d_ff": 3968, | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "layer_norm_bias": false, | |
| "model_type": "pix2struct_vision_model", | |
| "num_attention_heads": 24, | |
| "num_channels": 3, | |
| "num_hidden_layers": 18, | |
| "patch_size": 16, | |
| "projection_dim": 768 | |
| } | |
| } | |