Instructions to use zjunlp/OneKE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zjunlp/OneKE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zjunlp/OneKE")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zjunlp/OneKE") model = AutoModelForCausalLM.from_pretrained("zjunlp/OneKE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zjunlp/OneKE with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zjunlp/OneKE" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zjunlp/OneKE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zjunlp/OneKE
- SGLang
How to use zjunlp/OneKE 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 "zjunlp/OneKE" \ --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": "zjunlp/OneKE", "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 "zjunlp/OneKE" \ --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": "zjunlp/OneKE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zjunlp/OneKE with Docker Model Runner:
docker model run hf.co/zjunlp/OneKE
Update README.md
Browse files
README.md
CHANGED
|
@@ -89,7 +89,7 @@ from transformers import (
|
|
| 89 |
GenerationConfig,
|
| 90 |
BitsAndBytesConfig
|
| 91 |
)
|
| 92 |
-
|
| 93 |
model_path = 'zjunlp/OneKE'
|
| 94 |
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
|
| 95 |
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
@@ -120,7 +120,7 @@ system_prompt = '<<SYS>>\nYou are a helpful assistant. 你是一个乐于助人
|
|
| 120 |
sintruct = "{\"instruction\": \"You are an expert in named entity recognition. Please extract entities that match the schema definition from the input. Return an empty list if the entity type does not exist. Please respond in the format of a JSON string.\", \"schema\": [\"person\", \"organization\", \"else\", \"location\"], \"input\": \"284 Robert Allenby ( Australia ) 69 71 71 73 , Miguel Angel Martin ( Spain ) 75 70 71 68 ( Allenby won at first play-off hole )\"}"
|
| 121 |
sintruct = '[INST] ' + system_prompt + sintruct + '[/INST]'
|
| 122 |
|
| 123 |
-
input_ids = tokenizer.encode(sintruct, return_tensors="pt")
|
| 124 |
input_length = input_ids.size(1)
|
| 125 |
generation_output = model.generate(input_ids=input_ids, generation_config=GenerationConfig(max_length=1024, max_new_tokens=512, return_dict_in_generate=True))
|
| 126 |
generation_output = generation_output.sequences[0]
|
|
|
|
| 89 |
GenerationConfig,
|
| 90 |
BitsAndBytesConfig
|
| 91 |
)
|
| 92 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 93 |
model_path = 'zjunlp/OneKE'
|
| 94 |
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
|
| 95 |
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
|
|
| 120 |
sintruct = "{\"instruction\": \"You are an expert in named entity recognition. Please extract entities that match the schema definition from the input. Return an empty list if the entity type does not exist. Please respond in the format of a JSON string.\", \"schema\": [\"person\", \"organization\", \"else\", \"location\"], \"input\": \"284 Robert Allenby ( Australia ) 69 71 71 73 , Miguel Angel Martin ( Spain ) 75 70 71 68 ( Allenby won at first play-off hole )\"}"
|
| 121 |
sintruct = '[INST] ' + system_prompt + sintruct + '[/INST]'
|
| 122 |
|
| 123 |
+
input_ids = tokenizer.encode(sintruct, return_tensors="pt").to(device)
|
| 124 |
input_length = input_ids.size(1)
|
| 125 |
generation_output = model.generate(input_ids=input_ids, generation_config=GenerationConfig(max_length=1024, max_new_tokens=512, return_dict_in_generate=True))
|
| 126 |
generation_output = generation_output.sequences[0]
|