README.md

---
language:
- en
- tr
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- sft
base_model: TURKCELL/Turkcell-LLM-7b-v1
datasets:
- umarigan/openhermes_tr
library_name: adapter-transformers
---

# Uploaded  model

- **Developed by:** umarigan
- **License:** apache-2.0
- **Finetuned from model :** TURKCELL/Turkcell-LLM-7b-v1

This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)


This  model is fine-tuned version of Trendyol chat v1.0 on openhermes dataset. The dataset translated from English to Turkish lanuage and trained by unsloth's mistral scripts.
Usage:


```
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation",
                model="umarigan/TURKCELL-LLM-7B-openhermes",
                #use_flash_attention_2=True
                )
# Generate text
q = "Weng bebek bakıcılığından saatte 12 dolar kazanıyor. Dün sadece 50 dakika bebek bakıcılığı yaptı. Ne kadar kazandı?"
sequences_rlhf = pipe(
    q,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=2048,
)
sequences_rlhf[0]['generated_text']

```