|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- gemma |
|
- trl |
|
base_model: unsloth/gemma-1.1-2b-it-bnb-4bit |
|
--- |
|
|
|
# Model Details: |
|
|
|
- This model was created by finetuning the [unsloth/gemma-1.1-2b-it-bnb-4bit](https://huggingface.co./unsloth/gemma-1.1-2b-it-bnb-4bit) model using the [coedit dataset](https://huggingface.co./datasets/grammarly/coedit) from Grammarly. |
|
- The finetuning was done following the fine-tuning notebook provided by Unsloth as a practice of finetuning using the coedit dataset. |
|
- The model was finetuned using the prompt format of the gemma-2b-it model. |
|
``` |
|
<start_of_turn>user |
|
Fix grammar in this sentence: A notable number of Chinese factories make piratical products by copying foreign products.<end_of_turn> |
|
<start_of_turn>model |
|
A notable number of Chinese factories make pirated products by copying foreign products.<end_of_turn> |
|
``` |
|
- The finetuning was done 2x faster by utilizing the Unsloth and Hugging Face's TRL library. |
|
|
|
# Limitations: |
|
The model was finetuned on a specific dataset (coedit) and may not generalize well to all Italian text generation tasks. Its performance may be limited compared to models trained on larger and more diverse datasets. |
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** gnokit |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/gemma-1.1-2b-it-bnb-4bit |
|
|
|
This gemma 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) |
|
|
