| --- |
| license: mit |
| language: |
| - de |
| tags: |
| - title generation |
| - headline-generation |
| - teaser generation |
| - keyword generation |
| - tweet generation |
| - news |
| inference: false |
| --- |
| |
| # snip-igel-100 |
|
|
| <!-- Provide a quick summary of what the model is/does. --> |
|
|
| snip-igel-100 |
| 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: 21min 57s |
| Cloud Provider: Vast.ai |
| Compute Region: Poland |
| Carbon Emitted: ~0.11 kg of CO2e |
