Text Generation
Transformers
Safetensors
multi_modality
multimodal
lora-merged
4-bit precision
16-bit
image-understanding
image-generation
Instructions to use kiel2/Kiel-2.1-Omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiel2/Kiel-2.1-Omni with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kiel2/Kiel-2.1-Omni")# pip install -U transformers accelerate # Load model directly from transformers import MultiModalityCausalLM model = MultiModalityCausalLM.from_pretrained("kiel2/Kiel-2.1-Omni", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kiel2/Kiel-2.1-Omni with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kiel2/Kiel-2.1-Omni" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kiel2/Kiel-2.1-Omni", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kiel2/Kiel-2.1-Omni
- SGLang
How to use kiel2/Kiel-2.1-Omni 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 "kiel2/Kiel-2.1-Omni" \ --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": "kiel2/Kiel-2.1-Omni", "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 "kiel2/Kiel-2.1-Omni" \ --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": "kiel2/Kiel-2.1-Omni", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kiel2/Kiel-2.1-Omni with Docker Model Runner:
docker model run hf.co/kiel2/Kiel-2.1-Omni
Download tokenizer_config.json from kiel2/Kiel-2.1-Omni: direct link, hf CLI and curl.
- Browser
- Download file 651 Bytes
-
https://huggingface.co/kiel2/Kiel-2.1-Omni/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://kiel2/Kiel-2.1-Omni/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/kiel2/Kiel-2.1-Omni/resolve/main/tokenizer_config.json
651 Bytes
| { | |
| "add_prefix_space": null, | |
| "backend": "tokenizers", | |
| "bos_token": "<|begin▁of▁sentence|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|end▁of▁sentence|>", | |
| "extra_special_tokens": [ | |
| "<image_placeholder>", | |
| "<patch_placeholder>", | |
| "<|ref|>", | |
| "<|/ref|>", | |
| "<|det|>", | |
| "<|/det|>", | |
| "<|grounding|>", | |
| "<|User|>", | |
| "<|Assistant|>" | |
| ], | |
| "is_local": false, | |
| "local_files_only": false, | |
| "model_max_length": 16384, | |
| "pad_token": "<|▁pad▁|>", | |
| "processor_class": "VLChatProcessor", | |
| "tokenizer_class": "LlamaTokenizer", | |
| "unk_token": null, | |
| "use_default_system_prompt": true | |
| } | |