Instructions to use Unbabel/TowerInstruct-7B-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Unbabel/TowerInstruct-7B-v0.2 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="Unbabel/TowerInstruct-7B-v0.2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Unbabel/TowerInstruct-7B-v0.2") model = AutoModelForCausalLM.from_pretrained("Unbabel/TowerInstruct-7B-v0.2") - Notebooks
- Google Colab
- Kaggle
padding side should be "left"
#4
by PaulLerner - opened
Hi,
I think that padding side should be "left" https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2/blob/main/tokenizer_config.json#L95
Best regards
jmprcp changed discussion status to closed
But the padding side is left in https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1/blob/main/tokenizer_config.json#L95
The v0.1 model is deprecated. The v0.2 is consistent with LLama-2.