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

Libraries

How to use Ellight/Lite-Oute-1-65M-smol-smoltalk with Transformers:

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

pipe = pipeline("text-generation", model="Ellight/Lite-Oute-1-65M-smol-smoltalk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

vLLM

How to use Ellight/Lite-Oute-1-65M-smol-smoltalk with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ellight/Lite-Oute-1-65M-smol-smoltalk"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ellight/Lite-Oute-1-65M-smol-smoltalk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ellight/Lite-Oute-1-65M-smol-smoltalk

SGLang

How to use Ellight/Lite-Oute-1-65M-smol-smoltalk 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 "Ellight/Lite-Oute-1-65M-smol-smoltalk" \
    --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": "Ellight/Lite-Oute-1-65M-smol-smoltalk",
		"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 "Ellight/Lite-Oute-1-65M-smol-smoltalk" \
        --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": "Ellight/Lite-Oute-1-65M-smol-smoltalk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Model Card for Lite-Oute-1-65M-smol-smoltalk

This model is a fine-tuned version of OuteAI/Lite-Oute-1-65M using smol-smoltalk dataset for 1 epoch. 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. It has been trained using TRL. Below the finetuned model is evaluated on common benchmarks.

Benchmarks:

Metric	Lite-Oute-1-65M	Lite-Oute-1-65M-smol-smoltalk	SmolLM2-135M-Instruct
HellaSwag	28.27	28.56	42.83
ARC (Average)	31.85	28.275	38.37
PIQA	60.45	59.47	66.7
Winogrande	51.7	53.59	51.54
MMLU	23.05	22.9	22.96

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="Ellight/Lite-Oute-1-65M-smol-smoltalk", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

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.

Framework versions

TRL: 0.12.1
Transformers: 4.46.3
Pytorch: 2.2.1+cu121
Datasets: 3.1.0
Tokenizers: 0.20.3

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 11

Safetensors

Model size

64.2M params

Tensor type

BF16

Model tree for Ellight/Lite-Oute-1-65M-smol-smoltalk

Base model

OuteAI/Lite-Oute-1-65M

Finetuned

(2)

this model

Quantizations

1 model

Ellight
/

Lite-Oute-1-65M-smol-smoltalk