|
--- |
|
license: mit |
|
language: |
|
- de |
|
tags: |
|
- title generation |
|
- headline-generation |
|
- teaser generation |
|
- keyword generation |
|
- tweet generation |
|
- news |
|
inference: false |
|
--- |
|
|
|
# snip-igel-10 |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
snip-igel-10 |
|
Version 1.0 / 13 April 2023 |
|
|
|
An adapter for [IGEL](https://huggingface.co/philschmid/instruct-igel-001) to generate german news snippets with human written instructions |
|
|
|
See [snip-igel-500](https://huggingface.co/snipaid/snip-igel-500) for the full model description. We repeated fine-tuning with gradually increased amounts of training data, to see the difference. |
|
|
|
# Environmental Impact |
|
Carbon emissions were estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact/#compute) presented in Lacoste et al. (2019). |
|
|
|
Hardware Type: RTX 4090 |
|
Hours used: 1min 59s |
|
Cloud Provider: Vast.ai |
|
Compute Region: Poland |
|
Carbon Emitted: ~0.05 kg of CO2e |
