|
--- |
|
base_model: unsloth/llama-3-8b-bnb-4bit |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- llama |
|
- gguf |
|
datasets: |
|
- Ken4070TiS/qubit_arXiv |
|
--- |
|
|
|
This model was made by the following step: |
|
1. Use a web crawler to collect the papers by using arXiv API. |
|
2. The searching keyword is "qubit AND (IBM OR IQM OR Rigetti)", the time range is 2018 - 2024. |
|
3. The data was corrected in the JSON with column' Title, Abstract, Authors, arXiv_id, Date, Author_company. |
|
4. Feed the JSON files to llama-3-8b-bnb-4bit and fine-tune the model by using unsloth on google colab, the GPU is A100 |
|
5. That's it! :) |
|
|
|
|
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** Ken4070TiS |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/llama-3-8b-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) |
