Edit model card

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.

Downloads last month
29
Safetensors
Model size
65M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for OuteAI/Lite-Oute-1-65M

Finetunes
7 models
Quantizations
3 models

Collections including OuteAI/Lite-Oute-1-65M