Instructions to use truehealth/LLaVar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use truehealth/LLaVar with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="truehealth/LLaVar")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("truehealth/LLaVar") model = AutoModelForCausalLM.from_pretrained("truehealth/LLaVar", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use truehealth/LLaVar with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "truehealth/LLaVar" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "truehealth/LLaVar", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/truehealth/LLaVar
- SGLang
How to use truehealth/LLaVar 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 "truehealth/LLaVar" \ --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": "truehealth/LLaVar", "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 "truehealth/LLaVar" \ --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": "truehealth/LLaVar", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use truehealth/LLaVar with Docker Model Runner:
docker model run hf.co/truehealth/LLaVar
Download preprocessor_config.json from truehealth/LLaVar: direct link, hf CLI and curl.
- Browser
- Download file 857 Bytes
-
https://huggingface.co/truehealth/LLaVar/resolve/refs%2Fpr%2F2/preprocessor_config.json
- Command line
-
hf download hf://truehealth/LLaVar@refs/pr/2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/truehealth/LLaVar/resolve/refs%2Fpr%2F2/preprocessor_config.json
857 Bytes
| { | |
| "_name_or_path": "SALT-NLP/LLaVAR_delta", | |
| "architectures": [ | |
| "LlavaLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 2048, | |
| "max_sequence_length": 2048, | |
| "mm_hidden_size": 1024, | |
| "mm_use_im_start_end": true, | |
| "mm_vision_select_layer": -2, | |
| "mm_vision_tower": "openai/clip-vit-large-patch14-336", | |
| "model_type": "llava", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "sep_image_conv_front": false, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.28.0.dev0", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": false, | |
| "use_mm_proj": true, | |
| "vocab_size": 32003 | |
| } | |