Instructions to use Locutusque/UltraQwen-1_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/UltraQwen-1_8B with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/UltraQwen-1_8B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Locutusque/UltraQwen-1_8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/UltraQwen-1_8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/UltraQwen-1_8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/UltraQwen-1_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Locutusque/UltraQwen-1_8B

SGLang

How to use Locutusque/UltraQwen-1_8B 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 "Locutusque/UltraQwen-1_8B" \
    --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": "Locutusque/UltraQwen-1_8B",
		"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 "Locutusque/UltraQwen-1_8B" \
        --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": "Locutusque/UltraQwen-1_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Locutusque/UltraQwen-1_8B with Docker Model Runner:
```
docker model run hf.co/Locutusque/UltraQwen-1_8B
```

Model description

The model was trained on about 20,000 examples of the HuggingFaceH4/ultrachat_200k dataset, with plans to release more checkpoints later on.

This model has not been aligned with DPO. In the future, different repositories will be released that contain versions of this model aligned with DPO, using various datasets.

Evaluation

Upon personal testing, the model demonstrates excellent performance in mathematics, history, and coding tasks.

However, due to the model's requirement for the setting trust_remote_code=True, it cannot be submitted to the Open LLM Leaderboard. As a result, I will release a llama-fied version of this model that can be submitted to the Open LLM leaderboard.

Recommended inference parameters

temperature=0.2, top_p=0.14, top_k=12, repetition_penalty=1.1

License

Please make sure to read the Qwen licensing agreement before using this model.

Downloads last month: 40

Safetensors

Model size

2B params

Tensor type

F16

Model tree for Locutusque/UltraQwen-1_8B

Base model

Qwen/Qwen-1_8B

Finetuned

(5)

this model

Locutusque
/

UltraQwen-1_8B

Model description

Evaluation

Recommended inference parameters

License

Model tree for Locutusque/UltraQwen-1_8B

Dataset used to train Locutusque/UltraQwen-1_8B