Instructions to use oscar128372/Nova-0.5-e2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oscar128372/Nova-0.5-e2-7B with Transformers:

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

pipe = pipeline("text-generation", model="oscar128372/Nova-0.5-e2-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oscar128372/Nova-0.5-e2-7B")
model = AutoModelForCausalLM.from_pretrained("oscar128372/Nova-0.5-e2-7B")
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 oscar128372/Nova-0.5-e2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oscar128372/Nova-0.5-e2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oscar128372/Nova-0.5-e2-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oscar128372/Nova-0.5-e2-7B

SGLang

How to use oscar128372/Nova-0.5-e2-7B 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 "oscar128372/Nova-0.5-e2-7B" \
    --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": "oscar128372/Nova-0.5-e2-7B",
		"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 "oscar128372/Nova-0.5-e2-7B" \
        --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": "oscar128372/Nova-0.5-e2-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use oscar128372/Nova-0.5-e2-7B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for oscar128372/Nova-0.5-e2-7B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for oscar128372/Nova-0.5-e2-7B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for oscar128372/Nova-0.5-e2-7B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="oscar128372/Nova-0.5-e2-7B",
    max_seq_length=2048,
)

Docker Model Runner
How to use oscar128372/Nova-0.5-e2-7B with Docker Model Runner:
```
docker model run hf.co/oscar128372/Nova-0.5-e2-7B
```

Nova-0.5-e2-7B

Developed by: oscar128372
License: apache-2.0
Finetuned from model : oscar128372/Nova-0.5-e1-7B

This model uses the ChatML template:

<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
What is a famous tall tower in Paris?<|im_end|>
<|im_start|>assistant
The Eiffel Tower is a famous tall tower located in Paris, France. It was designed by Gustave Eiffel and completed in 1889 for the 1889 World's Fair. The Eiffel Tower is made of wrought iron and stands at a height of 324 meters (1,063 feet). It is one of the most recognizable landmarks in the world and attracts millions of visitors each year.<|im_end|>

Downloads last month: 4

Model tree for oscar128372/Nova-0.5-e2-7B

Base model

oscar128372/Nova-0.5-e1-7B

Finetuned

(1)

this model

Finetunes

2 models

Collection including oscar128372/Nova-0.5-e2-7B

Nova-7B

Collection

Collection of the Nova-7B series. • 6 items • Updated Mar 25, 2025 • 2