Instructions to use superqing/pangu-evolution with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use superqing/pangu-evolution with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="superqing/pangu-evolution", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("superqing/pangu-evolution", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use superqing/pangu-evolution with 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
- SGLang
How to use superqing/pangu-evolution 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 "superqing/pangu-evolution" \ --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": "superqing/pangu-evolution", "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 "superqing/pangu-evolution" \ --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": "superqing/pangu-evolution", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use superqing/pangu-evolution with Docker Model Runner:
docker model run hf.co/superqing/pangu-evolution
| { | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "GPTPanguForCausalLM" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 1024, | |
| "model_type": "gpt_pangu", | |
| "num_heads": 32, | |
| "num_layers": 32, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "tokenizer_class": "GPTPanguTokenizer", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.27.1", | |
| "use_cache": true, | |
| "vocab_size": 40000, | |
| "auto_map": { | |
| "AutoConfig": "configuration_gptpangu.GPTPanguConfig", | |
| "AutoTokenizer": ["tokenization_gptpangu.GPTPanguTokenizer", null], | |
| "AutoModelForCausalLM": "modeling_gptpangu.GPTPanguForCausalLM" | |
| }, | |
| "pad_token_id": 6 | |
| } | |