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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-1-65M-Instruct")
model = AutoModelForCausalLM.from_pretrained("OuteAI/Lite-Oute-1-65M-Instruct")
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 OuteAI/Lite-Oute-1-65M-Instruct 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-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OuteAI/Lite-Oute-1-65M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use OuteAI/Lite-Oute-1-65M-Instruct with Docker Model Runner:
```
docker model run hf.co/OuteAI/Lite-Oute-1-65M-Instruct
```

Train this model

by shikhardadhich - opened Jul 30, 2024

Discussion

shikhardadhich

Jul 30, 2024

How to train this model using Autotrain. I have data set of Linux commands with three column "number", "text" and "description" when I am running this with Autotrain getting this error
ERROR | 2024-07-30 10:49:51 | autotrain.trainers.common:wrapper:121 - Error occurred while packing the dataset. Make sure that your dataset has enough samples to at least yield one packed sequence.

edwko

OuteAI org Jul 30, 2024

•

edited Jul 30, 2024

Hi,
While I don't personally use Autotrain, from the error message, it looks like you're encountering an issue with your dataset rather than the model itself.
It's possible you're formatting your data incorrectly, or perhaps the block length is set too large for the amount of data you have. You might want to try different datasets to see which one works, then align your data to match that format. Also, as this is an instruct model, make sure you format your dataset with the ChatML template.

shikhardadhich

Jul 30, 2024

Thanks for your response. In case you have some sample data which I could refer for formatting, that would be great.

shikhardadhich changed discussion status to closed Jul 30, 2024

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