Instructions to use Terry0320/Kestrel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Terry0320/Kestrel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Terry0320/Kestrel")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Terry0320/Kestrel", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Terry0320/Kestrel with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Terry0320/Kestrel" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Terry0320/Kestrel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Terry0320/Kestrel
- SGLang
How to use Terry0320/Kestrel 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 "Terry0320/Kestrel" \ --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": "Terry0320/Kestrel", "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 "Terry0320/Kestrel" \ --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": "Terry0320/Kestrel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Terry0320/Kestrel with Docker Model Runner:
docker model run hf.co/Terry0320/Kestrel
working in progress
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "Terry0320/Kestrel"
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
sequences = pipeline(
"Generelativa is obsessed with general relativity and believes that it is the greatest theory in the world. He thinks that any other theory, including special relativity, is simply not worth mentioning.\nHoward: Hello, Generelativa!\nGenerelativa:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")