Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

alt text

Model Card for CARETTA

Cypien AI for Reducing Emissions and Technological Transition Assistance (CARETTA)

This model card provides information about the CARETTA, which is designed for text-generation tasks in Turkish. It emphasizes green sustainability, carbon emissions, and overall sustainability in its training and deployment.

Model Details

Model Description

CARETTA is a cutting-edge language model developed by the Cypien AI Team, optimized for text-generation tasks in the Turkish language. With a focus on green sustainability, this model aims to minimize carbon emissions associated with large-scale AI models without compromising performance. The model leverages the transformers library and is available under the Apache-2.0 license.

  • Developed by: Cypien AI Team
  • Model type: Language Model for Text-Generation
  • Language(s) (NLP): Turkish
  • License: Apache-2.0
  • **Finetuned from model: Mistral-7b architecture

Direct Use

This model is designed for direct use in carbon emission and energy systems applications requiring Turkish language understanding, RAG and text-generation capabilities. It can be integrated into chatbots, virtual assistants, and other AI systems where understanding and generating human-like responses in Turkish is essential.

Out-of-Scope Use

The model is not intended for use in critical systems where incorrect answers could lead to harm or in contexts that require domain-specific knowledge beyond the scope of general text-generation.

Bias, Risks, and Limitations

The model, like all AI models, may inherit biases from its training data. Users should be aware of these potential biases and consider them when integrating the model into applications.


To get started with the model, you can use the following code snippet in a Python environment with the transformers library installed:

How to Get Started with the Model

To get started with the model, you can use the following code snippet in a Python environment with the transformers library installed:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "cypienai/Caretta"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token_id = tokenizer.eos_token_id

Use Flash-Attention 2 to further speed-up generation

First make sure to install flash-attn. Refer to the original repository of Flash Attention regarding that package installation. Simply change the snippet above with:

model = AutoModelForCausalLM.from_pretrained(

You may also try it on Google Colab

Open In Colab

Example usage

Here's the prompt template for this model:

prompt= f"[INST] {base_instruction}\n\n{question} [/INST]"

You can use the model like following:

base_instruction="Sen, karbon ayak izi hakkındaki soruları yanıtlayan bir Dil Modelisin (LLM)"
question="Yenilenebilir gıdalar nelerdir ?"
prompt= f"[INST] {base_instruction}\n\n{question} [/INST]"

with torch.inference_mode():
  input_ids = tokenizer(prompt, return_tensors="pt").to(device)
  output = model.generate(**input_ids, max_new_tokens=8096)
  decoded_output = tokenizer.decode(output[0], skip_special_tokens=False)

Training Details

Training Data

The model was trained on a diverse set of Turkish language sources, encompassing a wide range of topics to ensure comprehensive language understanding.

Training Procedure


The training data underwent standard NLP preprocessing steps, including tokenization, normalization, and possibly data augmentation to enhance the model's robustness.

Training Hyperparameters

  • Learning Rate: 2e-4
  • Per Device Train Batch Size: 4
  • Trainable Params: 167,772,160
  • Total Params: 7,409,504,256
  • Trainable Params Percentage: 2.264%

Environmental Impact

The training of Caretta was conducted with a focus on minimizing carbon emissions. Detailed carbon emission statistics will be provided based on the Machine Learning Impact calculator, considering hardware type, usage hours, cloud provider, compute region, and total emissions.

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Technical Specifications

More detailed technical specifications, including model architecture, compute infrastructure, hardware, and software, will be provided to offer insights into the model's operational context.


When citing this model in your research, please refer to this model card for information about the model's development and capabilities.


A glossary section can be added to define specific terms and calculations related to the model, ensuring clarity for all potential users.

More Information [optional]

For more information or inquiries about the model, please contact the Cypien AI Team.

Model Card Contact


Downloads last month
Model size
7.24B params
Tensor type