How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "superqing/pangu-evolution"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "superqing/pangu-evolution",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/superqing/pangu-evolution
Quick Links

Configuration Parsing Warning:In UNKNOWN_FILENAME: "auto_map.AutoTokenizer" must be a string

Introduction

PanGu-Alpha-Evolution is an enhanced version of Pangu-Alpha, which can better understand and process tasks, and better follow your task description. More technical details will be updated continuously, please pay attention. [Technical report]

Use

  from transformers import AutoTokenizer, AutoModelForCausalLM
  tokenizer = AutoTokenizer.from_pretrained("superqing/pangu-evolution")
  model = AutoModelForCausalLM.from_pretrained("superqing/pangu-evolution", trust_remote_code=True)
Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support