Instructions to use dreamgen/lucid-v1-nemo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dreamgen/lucid-v1-nemo with Transformers:

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

pipe = pipeline("text-generation", model="dreamgen/lucid-v1-nemo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dreamgen/lucid-v1-nemo")
model = AutoModelForCausalLM.from_pretrained("dreamgen/lucid-v1-nemo", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dreamgen/lucid-v1-nemo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dreamgen/lucid-v1-nemo

SGLang

How to use dreamgen/lucid-v1-nemo 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 "dreamgen/lucid-v1-nemo" \
    --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": "dreamgen/lucid-v1-nemo",
		"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 "dreamgen/lucid-v1-nemo" \
        --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": "dreamgen/lucid-v1-nemo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use dreamgen/lucid-v1-nemo 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 dreamgen/lucid-v1-nemo 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 dreamgen/lucid-v1-nemo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dreamgen/lucid-v1-nemo to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="dreamgen/lucid-v1-nemo",
    max_seq_length=2048,
)

Docker Model Runner
How to use dreamgen/lucid-v1-nemo with Docker Model Runner:
```
docker model run hf.co/dreamgen/lucid-v1-nemo
```

Fantastic model but

by zhuregson - opened Apr 30, 2025

Discussion

zhuregson

Apr 30, 2025

I'm using this model on lmstudios, and the messages can get very very long. i've tried using ooc to reduce messages to below 200 or 300 words, but it doesn't seem to work right. i've had to reduce token count instead, but it cuts it off mid sentence. any thoughts on what i can do? thanks.

DreamGenX

DreamGen org Apr 30, 2025

Hey there! Glad you like the model.

I do not think it's possible to do instructions (OOC) properly (using the correct message header) in LMStudio, so that's likely why it did not work.

Instead, you can also control the message length using ## Writing Style section in system prompt. See here for details:

Reducing token count has no effect on the output style -- it just stops the model after N tokens, which explains why it gets cut off.

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