Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ This repo contains the experimental-educational fine-tuned model for the Turkish
|
|
| 20 |
|
| 21 |
The actual trained model is an adapter model of [Unsloth's Llama 3-8B quantized model](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit), which is then converted into .gguf format using llama.cpp and into .bin format for vLLM.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
You can access the fine-tuning code [here](https://colab.research.google.com/drive/1QRaqYxjfnFvwA_9jb7V0Z5bJr-PuHH7w?usp=sharing).
|
| 24 |
|
| 25 |
Trained with NVIDIA L4 with 150 steps, took around 8 minutes.
|
|
|
|
| 20 |
|
| 21 |
The actual trained model is an adapter model of [Unsloth's Llama 3-8B quantized model](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit), which is then converted into .gguf format using llama.cpp and into .bin format for vLLM.
|
| 22 |
|
| 23 |
+
The model is open to further development, we will continue to train the model when we obtain quality data. We can't use every Turkish dataset since some of them has poor quality of translation from English.
|
| 24 |
+
|
| 25 |
You can access the fine-tuning code [here](https://colab.research.google.com/drive/1QRaqYxjfnFvwA_9jb7V0Z5bJr-PuHH7w?usp=sharing).
|
| 26 |
|
| 27 |
Trained with NVIDIA L4 with 150 steps, took around 8 minutes.
|