|
--- |
|
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- llama |
|
- gguf |
|
--- |
|
|
|
# Model Description |
|
|
|
This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-bnb-4bit) on [cognitivecomputations/Code-290k-ShareGPT-Vicuna](https://huggingface.co/datasets/cognitivecomputations/Code-290k-ShareGPT-Vicuna) in order to answer questions related to programming better. Trained by the [Google Colab Notebook](https://colab.research.google.com/drive/1NYMWMe2Q11fQI3r6bPmOEbQd73sG9GW1?usp=sharing) provided by Unsloth with small modifications. |
|
Dataset format was converted from ShareGPT to [Llama 3](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/) in the training notebook. First 10k rows was used in training for demonstration purposes. |
|
- **Developed by:** [Can Deniz Koçak](https://www.linkedin.com/in/candenizkocak/) |
|
- **Finetuned from model:** [unsloth/Meta-Llama-3.1-8B-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-bnb-4bit) |
|
|
|
|
|
### Fine-tuning Data |
|
|
|
[cognitivecomputations/Code-290k-ShareGPT-Vicuna](https://huggingface.co/datasets/cognitivecomputations/Code-290k-ShareGPT-Vicuna) |
|
|
|
### Training Procedure |
|
|
|
Trained on a single A100 on Google Colab. |
|
<a target="_blank" href="https://colab.research.google.com/drive/1NYMWMe2Q11fQI3r6bPmOEbQd73sG9GW1?usp=sharing"> |
|
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> |
|
</a> |
|
- **Developed by:** candenizkocak |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit |
|
|
|
This llama 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) |
|
|
