README.md

---
license: llama3.1
language:
- tr
base_model: meta-llama/Meta-Llama-3.1-8B
---
<img src="https://cdn-uploads.huggingface.co/production/uploads/6639e48c27ef2d37a71eb4aa/Ds_KOVYwhRQ1FQY8S4WqO.png"
alt="CEREBRUM LLM" width="420"/>


# CERE V2 -LLMA-3.1-8b-TR

This model is an fine-tuned version of a Llama3.1 8b Large Language Model (LLM) for Turkish. It was trained on a high quality Turkish instruction sets created from various open-source and internal resources. Turkish Instruction dataset carefully annotated to carry out Turkish instructions in an accurate and organized manner. 

## Model Details

- **Base Model**: LLMA 3.1 8B based LLM
- **Tokenizer Extension**: Specifically extended for Turkish
- **Training Dataset**: Cleaned Turkish raw data with 5 billion tokens, custom Turkish instruction sets
- **Training Method**: Initially with DORA, followed by fine-tuning with LORA

## Benchmark Results

- **Winogrande_tr**: 56.16
- **TruthfulQA_tr_v0.2**: 47.46
- **Mmlu_tr_v0.2**: 46.46
- **HellaSwag_tr_v0.2**: 48.87
- **GSM8k_tr_v0.2**: 25.43
- **Arc_tr_v0.2**: 41.97


## Usage Examples

```python

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "Cerebrum/cere-llama-3.1-8B-tr",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Cerebrum/cere-llama-3.1-8B-tr")

prompt = "Python'da ekrana 'Merhaba Dünya' nasıl yazılır?"
messages = [
    {"role": "system", "content": "Sen, Cerebrum Tech tarafından üretilen ve verilen talimatları takip ederek en iyi cevabı üretmeye çalışan yardımcı bir yapay zekasın."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    temperature=0.3,
    top_k=50,
    top_p=0.9,
    max_new_tokens=512,
    repetition_penalty=1,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```