Instructions to use xiaoyewuz-Ruster/zzjrabbit3-pre1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xiaoyewuz-Ruster/zzjrabbit3-pre1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xiaoyewuz-Ruster/zzjrabbit3-pre1", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("xiaoyewuz-Ruster/zzjrabbit3-pre1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xiaoyewuz-Ruster/zzjrabbit3-pre1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xiaoyewuz-Ruster/zzjrabbit3-pre1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xiaoyewuz-Ruster/zzjrabbit3-pre1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/xiaoyewuz-Ruster/zzjrabbit3-pre1
- SGLang
How to use xiaoyewuz-Ruster/zzjrabbit3-pre1 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 "xiaoyewuz-Ruster/zzjrabbit3-pre1" \ --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": "xiaoyewuz-Ruster/zzjrabbit3-pre1", "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 "xiaoyewuz-Ruster/zzjrabbit3-pre1" \ --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": "xiaoyewuz-Ruster/zzjrabbit3-pre1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use xiaoyewuz-Ruster/zzjrabbit3-pre1 with Docker Model Runner:
docker model run hf.co/xiaoyewuz-Ruster/zzjrabbit3-pre1
Download config.json from xiaoyewuz-Ruster/zzjrabbit3-pre1: direct link, hf CLI and curl.
- Browser
- Download file 450 Bytes
-
https://huggingface.co/xiaoyewuz-Ruster/zzjrabbit3-pre1/resolve/main/config.json
- Command line
-
hf download hf://xiaoyewuz-Ruster/zzjrabbit3-pre1/config.json
-
curl -L -o config.json https://huggingface.co/xiaoyewuz-Ruster/zzjrabbit3-pre1/resolve/main/config.json
450 Bytes
| { | |
| "architectures": [ | |
| "ZZJRabbit3ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "zzjrabbit3.ZZJRabbit3Config", | |
| "AutoModelForCausalLM": "zzjrabbit3.ZZJRabbit3ForCausalLM" | |
| }, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 0, | |
| "hidden_size": 1024, | |
| "model_type": "zzjrabbit3", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "transformers_version": "5.3.0", | |
| "vocab_size": 100000 | |
| } | |