Instructions to use rxavier/Taurus-7B-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rxavier/Taurus-7B-1.0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rxavier/Taurus-7B-1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rxavier/Taurus-7B-1.0")
model = AutoModelForCausalLM.from_pretrained("rxavier/Taurus-7B-1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rxavier/Taurus-7B-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rxavier/Taurus-7B-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rxavier/Taurus-7B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rxavier/Taurus-7B-1.0

SGLang

How to use rxavier/Taurus-7B-1.0 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 "rxavier/Taurus-7B-1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rxavier/Taurus-7B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "rxavier/Taurus-7B-1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rxavier/Taurus-7B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rxavier/Taurus-7B-1.0 with Docker Model Runner:
```
docker model run hf.co/rxavier/Taurus-7B-1.0
```

Taurus-7B-1.0

Commit History

Update README.md

b2f2f15
verified

rxavier commited on Mar 17, 2024

Update README.md

f2a9f5c
verified

rxavier commited on Mar 17, 2024

Update README.md

9cde966
verified

rxavier commited on Mar 9, 2024

Adding Evaluation Results (#1)

5ffaba9
verified

rxavier

leaderboard-pr-bot commited on Mar 4, 2024

Update README.md

850ff44
verified

rxavier commited on Feb 25, 2024