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

Libraries

How to use LucidityAI/Lumi-1 with Transformers:

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

pipe = pipeline("text-generation", model="LucidityAI/Lumi-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LucidityAI/Lumi-1")
model = AutoModelForCausalLM.from_pretrained("LucidityAI/Lumi-1")
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 LucidityAI/Lumi-1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LucidityAI/Lumi-1

SGLang

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

Docker Model Runner
How to use LucidityAI/Lumi-1 with Docker Model Runner:
```
docker model run hf.co/LucidityAI/Lumi-1
```

sd-inf commited on Mar 14, 2025

Commit

df4c80c

verified ·

1 Parent(s): 2c9459f

(Trained with Unsloth)

Browse files

Files changed (5) hide show

config.json +1 -1
generation_config.json +1 -1
pytorch_model-00001-of-00002.bin +2 -2
pytorch_model-00002-of-00002.bin +2 -2
tokenizer.json +2 -2

config.json CHANGED Viewed

@@ -24,7 +24,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
   "transformers_version": "4.48.3",
-  "unsloth_version": "2025.3.10",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

   "tie_word_embeddings": true,
   "torch_dtype": "float16",
   "transformers_version": "4.48.3",
+  "unsloth_version": "2025.3.14",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json CHANGED Viewed

@@ -3,6 +3,6 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "max_length": 32768,
-  "pad_token_id": 151643,
   "transformers_version": "4.48.3"
 }

   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "max_length": 32768,
+  "pad_token_id": 0,
   "transformers_version": "4.48.3"
 }

pytorch_model-00001-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8973afad35b36f752aab5fcdd911229b367ceceecbf343e4a45997dad495b29
-size 4957642530

 version https://git-lfs.github.com/spec/v1
+oid sha256:67689a4394569bac59145584912dbd3c26be8a49b4ad0054d4dd78c12613280a
+size 4957629200

pytorch_model-00002-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4874e24d36da918f53c75509864a36dcf88f39265139634eeb4b684f13cba4
-size 1214388222

 version https://git-lfs.github.com/spec/v1
+oid sha256:24c60fa17ec230246e147f437eccb8405c6d4fd7c58efd9db17c4e76b839fe11
+size 1214384514

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

 version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063