Instructions to use Samvardhan777/gemma-2b-mt-German-to-English with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Samvardhan777/gemma-2b-mt-German-to-English with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="Samvardhan777/gemma-2b-mt-German-to-English")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Samvardhan777/gemma-2b-mt-German-to-English") model = AutoModelForCausalLM.from_pretrained("Samvardhan777/gemma-2b-mt-German-to-English", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Description
Gemma 2B German to English v0.1 Alpha [Experimental Release]
This is a german instruction finetuned version of Google's Gemma 2B model. This is an experiment to see if Gemma can be Translate German to English by expanding vocabulary. While the responses may be rusty at times, it shows a lot of promise for a 2B parameter model.
Model description ποΈ:
Model type: A 2B parameter GPT-like model finetuned on 100,000 samples consisting of an equal proportion of English and German samples.
Language(s): Bilingual. English and German.
License: Google Gemma Terms of Use
Finetuned from model: Samvardhan777/gemma-2b-mt-German-to-English
Training Precision: bfloat16
Training Hardware: Free Google Colab
Dataset: kaitchup/opus-German-to-English
- Downloads last month
- 20