Instructions to use OuteAI/Lite-Oute-1-65M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OuteAI/Lite-Oute-1-65M with Transformers:

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

pipe = pipeline("text-generation", model="OuteAI/Lite-Oute-1-65M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-1-65M")
model = AutoModelForCausalLM.from_pretrained("OuteAI/Lite-Oute-1-65M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OuteAI/Lite-Oute-1-65M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OuteAI/Lite-Oute-1-65M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OuteAI/Lite-Oute-1-65M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OuteAI/Lite-Oute-1-65M

SGLang

How to use OuteAI/Lite-Oute-1-65M 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 "OuteAI/Lite-Oute-1-65M" \
    --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": "OuteAI/Lite-Oute-1-65M",
		"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 "OuteAI/Lite-Oute-1-65M" \
        --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": "OuteAI/Lite-Oute-1-65M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OuteAI/Lite-Oute-1-65M with Docker Model Runner:
```
docker model run hf.co/OuteAI/Lite-Oute-1-65M
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OuteAI

🌎 OuteAI.com 🤝 Join our Discord 𝕏 @OuteAI

Lite-Oute-1-65M

Lite-Oute-1-65M (Base) is an experimental ultra-compact base model in the Lite series, built on the LLaMA architecture and comprising approximately 65 million parameters.
This model is intended as a starting point for fine-tuning on highly specific or narrow tasks.
Due to its extremely small size, this model demonstrates basic text generation abilities but struggle with instructions or maintaining topic coherence.

Available versions:

Lite-Oute-1-65M-Instruct
Lite-Oute-1-65M-Instruct-GGUF
Lite-Oute-1-65M
Lite-Oute-1-65M-GGUF

Benchmarks:

Benchmark	5-shot	0-shot
ARC Challenge	21.42	22.44
ARC Easy	38.34	41.25
CommonsenseQA	18.84	19.49
HellaSWAG	28.30	28.27
MMLU	25.44	23.05
OpenBookQA	26.20	27.60
PIQA	60.17	60.45
Winogrande	51.22	51.70

Usage with HuggingFace transformers

The model can be used with HuggingFace's transformers library:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained("OuteAI/Lite-Oute-1-65M").to(device)
tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-1-65M")
def generate_response(message: str, temperature: float = 0.4, repetition_penalty: float = 1.12) -> str:
    # Convert message to PyTorch tensors
    input_ids = tokenizer.encode(
        message, return_tensors="pt"
    ).to(device)
    # Generate the response
    output = model.generate(
        input_ids,
        max_length=256,
        temperature=temperature,
        repetition_penalty=repetition_penalty,
        do_sample=True
    ) 
    # Decode the generated output
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
    return generated_text
message = "Scientists have made a breakthrough in renewable energy by developing a new type of"
response = generate_response(message)
print(response)

Risk Disclaimer

By using this model, you acknowledge that you understand and assume the risks associated with its use. You are solely responsible for ensuring compliance with all applicable laws and regulations. We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages. We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.