Instructions to use Marqo/gcl-e5-large-v2-113-gs-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Marqo/gcl-e5-large-v2-113-gs-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Marqo/gcl-e5-large-v2-113-gs-full")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Marqo/gcl-e5-large-v2-113-gs-full") model = AutoModel.from_pretrained("Marqo/gcl-e5-large-v2-113-gs-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Clarification
#1
by omarabb315 - opened
what is the difference between these two models, and which is better?
Marqo/gcl-e5-large-v2-113-gs-full
Marqo/marqo-gcl-e5-large-v2-130
The 130 one has batch size of 3072, 113 has batch size of 2048.
130 has better metrics under gs evaluation.
alanztymarqo changed discussion status to closed