Image-Text-to-Text
Transformers
Safetensors
English
Emu3
text-generation
visual-reasoning
unified-model
reinforcement-learning
emu3.5
multimodal
next-token-prediction
grpo
Instructions to use UniVRBD/UniVR-34B-General with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UniVRBD/UniVR-34B-General with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="UniVRBD/UniVR-34B-General")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("UniVRBD/UniVR-34B-General", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use UniVRBD/UniVR-34B-General with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UniVRBD/UniVR-34B-General" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "UniVRBD/UniVR-34B-General", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/UniVRBD/UniVR-34B-General
- SGLang
How to use UniVRBD/UniVR-34B-General 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 "UniVRBD/UniVR-34B-General" \ --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": "UniVRBD/UniVR-34B-General", "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 "UniVRBD/UniVR-34B-General" \ --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": "UniVRBD/UniVR-34B-General", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use UniVRBD/UniVR-34B-General with Docker Model Runner:
docker model run hf.co/UniVRBD/UniVR-34B-General
| { | |
| "architectures": [ | |
| "Emu3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "boi_token_id": 151852, | |
| "bos_token_id": 151849, | |
| "dtype": "bfloat16", | |
| "eof_token_id": 151847, | |
| "eoi_token_id": 151853, | |
| "eol_token_id": 151846, | |
| "eos_token_id": 151850, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "image_area": 518400, | |
| "img_token_id": 151851, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 25600, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "Emu3", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 282926 | |
| } | |