Image-Text-to-Text
Transformers
Safetensors
llava_next
unlearning
wmdp
multimodal
conversational
text-generation-inference
Instructions to use HoshiuZ/LLaVA-NeXT-8B-Unlearned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HoshiuZ/LLaVA-NeXT-8B-Unlearned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="HoshiuZ/LLaVA-NeXT-8B-Unlearned") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("HoshiuZ/LLaVA-NeXT-8B-Unlearned") model = AutoModelForMultimodalLM.from_pretrained("HoshiuZ/LLaVA-NeXT-8B-Unlearned", device_map="auto") 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?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HoshiuZ/LLaVA-NeXT-8B-Unlearned with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HoshiuZ/LLaVA-NeXT-8B-Unlearned" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HoshiuZ/LLaVA-NeXT-8B-Unlearned", "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/HoshiuZ/LLaVA-NeXT-8B-Unlearned
- SGLang
How to use HoshiuZ/LLaVA-NeXT-8B-Unlearned 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 "HoshiuZ/LLaVA-NeXT-8B-Unlearned" \ --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": "HoshiuZ/LLaVA-NeXT-8B-Unlearned", "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 "HoshiuZ/LLaVA-NeXT-8B-Unlearned" \ --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": "HoshiuZ/LLaVA-NeXT-8B-Unlearned", "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 HoshiuZ/LLaVA-NeXT-8B-Unlearned with Docker Model Runner:
docker model run hf.co/HoshiuZ/LLaVA-NeXT-8B-Unlearned
Download config.json from HoshiuZ/LLaVA-NeXT-8B-Unlearned: direct link, hf CLI and curl.
- Browser
- Download file 1.88 kB
-
https://huggingface.co/HoshiuZ/LLaVA-NeXT-8B-Unlearned/resolve/main/config.json
- Command line
-
hf download hf://HoshiuZ/LLaVA-NeXT-8B-Unlearned/config.json
-
curl -L -o config.json https://huggingface.co/HoshiuZ/LLaVA-NeXT-8B-Unlearned/resolve/main/config.json
1.88 kB
| { | |
| "architectures": [ | |
| "LlavaNextForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "ignore_index": -100, | |
| "image_grid_pinpoints": [ | |
| [ | |
| 336, | |
| 672 | |
| ], | |
| [ | |
| 672, | |
| 336 | |
| ], | |
| [ | |
| 672, | |
| 672 | |
| ], | |
| [ | |
| 1008, | |
| 336 | |
| ], | |
| [ | |
| 336, | |
| 1008 | |
| ] | |
| ], | |
| "image_seq_length": 576, | |
| "image_token_index": 128256, | |
| "model_type": "llava_next", | |
| "multimodal_projector_bias": true, | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "_name_or_path": "HoshiuZ/LLaVA-NeXT-8B-Unlearned", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 128009, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "use_cache": true, | |
| "vocab_size": 128320 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "use_image_newline_parameter": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 1024, | |
| "image_size": 336, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768, | |
| "vocab_size": 32000 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "default" | |
| } | |