Instructions to use Q-bert/Optimus-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Q-bert/Optimus-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Q-bert/Optimus-7B")
model = AutoModelForCausalLM.from_pretrained("Q-bert/Optimus-7B")
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

vLLM

How to use Q-bert/Optimus-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Q-bert/Optimus-7B

SGLang

How to use Q-bert/Optimus-7B 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 "Q-bert/Optimus-7B" \
    --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": "Q-bert/Optimus-7B",
		"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 "Q-bert/Optimus-7B" \
        --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": "Q-bert/Optimus-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Q-bert/Optimus-7B with Docker Model Runner:
```
docker model run hf.co/Q-bert/Optimus-7B
```

Q-bert

cherry0328 commited on Jan 6

Commit

a769e9a

verified ·

1 Parent(s): 3f4d59c

Update README.md (#3)

Browse files

- Update README.md (9a5ca1421917617e09c35f8f5f049e2acf2df77a)

Co-authored-by: cherry0328 <cherry0328@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -7,6 +7,8 @@ language:
 pipeline_tag: text-generation
 tags:
 - Math
 ---
 ## Optimus-7B
@@ -28,5 +30,4 @@ Detailed results can be found [Here](https://huggingface.co/datasets/open-llm-le
 | MMLU (5-shot)         | 63.61               |
 | TruthfulQA (0-shot)   | 55.79               |
 | Winogrande (5-shot)   | 78.77               |
-| GSM8K (5-shot)        | 65.50               |

 pipeline_tag: text-generation
 tags:
 - Math
+base_model:
+- mistralai/Mistral-7B-v0.1
 ---
 ## Optimus-7B
 | MMLU (5-shot)         | 63.61               |
 | TruthfulQA (0-shot)   | 55.79               |
 | Winogrande (5-shot)   | 78.77               |
+| GSM8K (5-shot)        | 65.50               |