---
base_model: boun-tabi-LMG/TURNA
language:
- tr
license: other
model_creator: boun-tabi-LMG
model_name: TURNA
model_type: t5
prompt_template: '[S2S]prompt<EOS>'
quantized_by: Furkan Erdi
tags:
- GGUF
- Transformers
- TURNA
- t5
library_name: transformers
architecture: t5
inference: false
---

# TURNA - GGUF
- Model creator: [boun-tabi-LMG](https://huggingface.co/boun-tabi-LMG)
- Original model: [TURNA](https://huggingface.co/boun-tabi-LMG/TURNA)

<!-- description start -->
## Description

This repo contains GGUF format model files for [boun-tabi-LMG's TURNA](https://huggingface.co/boun-tabi-LMG/TURNA).

<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

<!-- README_GGUF.md-about-gguf end -->

<!-- prompt-template start -->
## Prompt template

```
[S2S]prompt<EOS>
```

<!-- prompt-template end -->


<!-- compatibility_gguf start -->
## Compatibility

These quantised GGUFv2 files are compatible with candle from huggingface.

Those models are quantized by candle, cargo using Rust and Python.

<!-- compatibility_gguf end -->

<!-- README_GGUF.md-provided-files start -->
## Provided files

| Name | Bit | Quant Method | Size | Use case |
| ---- | ---- | ---- | ---- | ---- |
| [TURNA_Q2K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q2K.gguf) | 2 | Q2K | 0.36 GB | Smallest size, lowest precision |
| [TURNA_Q3K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q3K.gguf) | 3 | Q3K | 0.48 GB | Very low precision |
| [TURNA_Q4_0.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q4_0.gguf) | 4 | Q4_0 | 0.63 GB | Low precision, level 0 |
| [TURNA_Q4_1.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q4_1.gguf) | 4 | Q4_1 | 0.70 GB | Slightly better than Q4_0 |
| [TURNA_Q4K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q4K.gguf) | 4 | Q4K | 0.63 GB | Kernel optimized, low precision |
| [TURNA_Q5_0.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q5_0.gguf) | 5 | Q5_0 | 0.77 GB | Moderate precision, level 0 |
| [TURNA_Q5_1.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q5_1.gguf) | 5 | Q5_1 | 0.84 GB | Better than Q5_0 |
| [TURNA_Q5K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q5K.gguf) | 5 | Q5K | 0.77 GB | Kernel optimized, moderate precision |
| [TURNA_Q6K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q6K.gguf) | 6 | Q6K | 0.91 GB | Higher precision than Q5K |
| [TURNA_Q8_0.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q8_0.gguf) | 8 | Q8_0 | 1.21 GB | High precision, level 0 |
| [TURNA_Q8_1.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q8_1.gguf) | 8 | Q8_1 | 1.29 GB | Better than Q8_0 |
| [TURNA_Q8K.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_Q8K.gguf) | 8 | Q8K | 1.30 GB | Kernel optimized, highest precision among quantized |
| [TURNA_F16.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_F16.gguf) | 16 | F16 | 2.28 GB | High precision, smaller size |
| [TURNA_F32.gguf](https://huggingface.co/helizac/TURNA_GGUF/blob/main/TURNA_F32.gguf) | 32 | F32 | 4.57 GB | Highest precision, largest size |

<!-- README_GGUF.md-provided-files end -->

# License

The model is shared with the public to be used solely for non-commercial academic research purposes.

<!-- README_GGUF.md-how-to-download start -->

## How to download GGUF files

**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

### On the command line, including multiple files at once

I recommend using the `huggingface-hub` Python library:

```shell
pip3 install huggingface-hub
```

Then you can download any individual model file to the current directory, at high speed, with a command like this:

```shell
huggingface-cli download helizac/TURNA_GGUF TURNA_Q4_K.gguf --local-dir . --local-dir-use-symlinks False
```

<details>
  <summary>More advanced huggingface-cli download usage (click to read)</summary>

You can also download multiple files at once with a pattern:

```shell
huggingface-cli download helizac/TURNA_GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```

For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).

</details>

<!-- README_GGUF.md-how-to-download end -->

<!-- README_GGUF.md-how-to-run start -->


# Example `colab` usage

```shell
%%shell
# Update and install dependencies
apt update && apt install -y curl build-essential
pip install huggingface_hub

# Install Rust using rustup
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y

# Add Rust to the PATH
source $HOME/.cargo/env

# Cloning Candle from Huggingface
git clone https://github.com/huggingface/candle.git

# Use read CLI or a CLI that has read permissions
huggingface-cli login
```

```shell
%cd candle
```

```python
def run_turna_gguf(prompt="Bir varmış bir yokmuş, ", temperature=1, quantization_method="Q8_1", config_file="config.json", model_id = "helizac/TURNA_GGUF"):
  os.system(f'cargo run --example quantized-t5 --release -- --model-id "{model_id}" --prompt "[S2S]{prompt}<EOS>" --temperature {temperature} --weight-file "TURNA_{quantization_method}.gguf" --config-file "{config_file}"')
```

```python
run_turna_gguf("Bir varmış bir yokmuş") # test
```

Sure, here's an explanation for the function `run_turna_gguf`:

### Function Explanation: `run_turna_gguf`

```python
def run_turna_gguf(prompt="Bir varmış bir yokmuş, ", temperature=1, quantization_method="Q8_1", config_file="config.json", model_id = "helizac/TURNA_GGUF"):
  os.system(f'cargo run --example quantized-t5 --release -- --model-id "{model_id}" --prompt "[S2S]{prompt}<EOS>" --temperature {temperature} --weight-file "TURNA_{quantization_method}.gguf" --config-file "{config_file}"')
```

#### Parameters:
- **prompt** (`str`, default: "Bir varmış bir yokmuş, "):
  - The initial text provided as input to the model.
- **temperature** (`float`, default: 1):
  - Controls the randomness of the output. Higher values make the output more random, while lower values make it more deterministic.
- **quantization_method** (`str`, default: "Q8_1"):
  - Specifies the quantization method to use. This selects the corresponding `.gguf` weight file.
- **config_file** (`str`, default: "config.json"):
  - The path to the configuration file containing model-specific settings.
- **model_id** (`str`, default: "helizac/TURNA_GGUF"):
  - The identifier for the model in the Hugging Face repository.

## Thanks, and how to contribute

Thanks to the [boun-tabi-LMG](https://github.com/boun-tabi-LMG) team!

<!-- footer end -->

# GGUF model card:

```
{Furkan Erdi}
```

<!-- original-model-card start -->
# Original model card: BOUN TABI Language Modeling Group's TURNA

TURNA 🦩

```
@misc{uludoğan2024turna,
      title={TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation}, 
      author={Gökçe Uludoğan and Zeynep Yirmibeşoğlu Balal and Furkan Akkurt and Melikşah Türker and Onur Güngör and Susan Üsküdarlı},
      year={2024},
      eprint={2401.14373},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```