Instructions to use Nora-006/QwenOlga with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nora-006/QwenOlga with Transformers:

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

pipe = pipeline("text-generation", model="Nora-006/QwenOlga")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nora-006/QwenOlga")
model = AutoModelForCausalLM.from_pretrained("Nora-006/QwenOlga", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nora-006/QwenOlga with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nora-006/QwenOlga"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nora-006/QwenOlga",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nora-006/QwenOlga

SGLang

How to use Nora-006/QwenOlga 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 "Nora-006/QwenOlga" \
    --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": "Nora-006/QwenOlga",
		"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 "Nora-006/QwenOlga" \
        --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": "Nora-006/QwenOlga",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nora-006/QwenOlga with Docker Model Runner:
```
docker model run hf.co/Nora-006/QwenOlga
```

Exemples de générations

by Nora-006 - opened Jan 28

Discussion

Nora-006

Owner Jan 28

Voici les résultats de générations :

The biggest of the world of the world, the life. the world, the is the the best the greatest of the same mistake in the
In conclusion:
The second of the world. the most of the most of the same the best of us to the same. the
A world of the people are the same of the world.
Some of the world, the world's the best.
The first:
TheThe British of the first impressions of that?

The first

The first first impressions of the first impressions of the first impression is the first job, or.
The first thing of that is the first.
One of the greatest the best of the world. The failure was the
Other of the best of the world of the park of the world. It was the life. The best.
The self-:
The three of the the failure:

The life for the the

A example:

People will a big behavior for a failure for for the enthusiasm in the

The second of the the world of the main. the
Success, the world can the world of the world.
The main thing to the world of the first, the
The the reason of the best of the problem of the world of the
The human:
The curfew is in the life of the world.
There is the world to the biggest of them.
Second of the truth of the second reason is the second of the technology is, the
The third of the city.
The first impressions of the world.
If the best to the best of the whole.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment