Instructions to use DreamhubAI/Nova-e-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamhubAI/Nova-e-mini with Transformers:

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

pipe = pipeline("text-generation", model="DreamhubAI/Nova-e-mini")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DreamhubAI/Nova-e-mini", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DreamhubAI/Nova-e-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DreamhubAI/Nova-e-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DreamhubAI/Nova-e-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DreamhubAI/Nova-e-mini

SGLang

How to use DreamhubAI/Nova-e-mini 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 "DreamhubAI/Nova-e-mini" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DreamhubAI/Nova-e-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "DreamhubAI/Nova-e-mini" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DreamhubAI/Nova-e-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use DreamhubAI/Nova-e-mini 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 DreamhubAI/Nova-e-mini 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 DreamhubAI/Nova-e-mini to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DreamhubAI/Nova-e-mini to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DreamhubAI/Nova-e-mini",
    max_seq_length=2048,
)

Docker Model Runner
How to use DreamhubAI/Nova-e-mini with Docker Model Runner:
```
docker model run hf.co/DreamhubAI/Nova-e-mini
```

sinamsv0 commited on Dec 8, 2025

Commit

87fab78

verified ·

1 Parent(s): c442de1

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -107,7 +107,7 @@ print(response[0]["generated_text"])
-🧪 Training Summary
 Method: Supervised Fine-Tuning (SFT)
@@ -122,16 +122,16 @@ Goal: Improve instruction-following, multilingual responses, and short-prompt be
-🛡 Safety & Limitations
-✅ Trained with safety-aware data
-✅ Avoids harmful or unethical requests
-⚠️ Limited reasoning depth due to 1B parameter size
-⚠️ Not intended for complex multi-step reasoning or creative writing
-🌍 Ideal Use Cases
 Local coding assistant
@@ -148,7 +148,7 @@ Research and experimentation with small LLMs
-🤝 Community & Links
 GitHub: https://github.com/unknownmsv/WALL-E
@@ -161,7 +161,7 @@ Hugging Face Space: https://huggingface.co/spaces/sinamsv0/WALL-E-DEMO
-🔮 Roadmap (Planned)
 UI tools for local use

+## 🧪 Training Summary
 Method: Supervised Fine-Tuning (SFT)
+## 🛡 Safety & Limitations
+- ✅ Trained with safety-aware data
+- ✅ Avoids harmful or unethical requests
+- ⚠️ Limited reasoning depth due to 1B parameter size
+- ⚠️ Not intended for complex multi-step reasoning or creative writing
+## 🌍 Ideal Use Cases
 Local coding assistant
+## 🤝 Community & Links
 GitHub: https://github.com/unknownmsv/WALL-E
+## 🔮 Roadmap (Planned)
 UI tools for local use