Instructions to use jclian91/Qwen2-72B-Instruct-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jclian91/Qwen2-72B-Instruct-math with Transformers:

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

pipe = pipeline("text-generation", model="jclian91/Qwen2-72B-Instruct-math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jclian91/Qwen2-72B-Instruct-math")
model = AutoModelForCausalLM.from_pretrained("jclian91/Qwen2-72B-Instruct-math", device_map="auto")
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 jclian91/Qwen2-72B-Instruct-math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jclian91/Qwen2-72B-Instruct-math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jclian91/Qwen2-72B-Instruct-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jclian91/Qwen2-72B-Instruct-math

SGLang

How to use jclian91/Qwen2-72B-Instruct-math 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 "jclian91/Qwen2-72B-Instruct-math" \
    --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": "jclian91/Qwen2-72B-Instruct-math",
		"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 "jclian91/Qwen2-72B-Instruct-math" \
        --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": "jclian91/Qwen2-72B-Instruct-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jclian91/Qwen2-72B-Instruct-math with Docker Model Runner:
```
docker model run hf.co/jclian91/Qwen2-72B-Instruct-math
```

Qwen2-72B-Instruct-math

Commit History

Update README.md

f45e906
verified

jclian91 commited on Sep 14, 2024

Update README.md

250bdd4
verified

jclian91 commited on Sep 14, 2024

Update README.md

9ac6e52
verified

jclian91 commited on Sep 14, 2024

Update README.md

485a819
verified

jclian91 commited on Sep 5, 2024

Update README.md

acd3fd4
verified

jclian91 commited on Sep 2, 2024

Update README.md

f65caec
verified

jclian91 commited on Aug 27, 2024

Update README.md

8d9a60c
verified

jclian91 commited on Aug 26, 2024

Update README.md

f1be7da
verified

jclian91 commited on Aug 26, 2024

Update README.md

799c2af
verified

jclian91 commited on Jul 4, 2024

Update README.md

efef09d
verified

jclian91 commited on Jul 4, 2024