Instructions to use llmrails/ember-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use llmrails/ember-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("llmrails/ember-v1") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use llmrails/ember-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="llmrails/ember-v1")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("llmrails/ember-v1") model = AutoModel.from_pretrained("llmrails/ember-v1") - Inference
- Notebooks
- Google Colab
- Kaggle
Technical Report
Hi! I'm currently manually reviewing the top 200 models on MTEB, and while your model has been available for approximately a year, your technical report remains to be published.
Can we expect to get more information on your training procedure and data? Perhaps a preprint?
I just wanted to follow up on this. We are doing in effort in MTEB to annotate training data on our leaderboard so that users can know how well models generalize to out-of-domain data.
Since I have failed to recover information about your training data, and the technical report is still not released, we display a warning to our users indicating that we can't be sure where your otherwise impressive scores come from.
I would appreciate, if you could get back to me about this, and indicate if, and which datasets, you have used from the MTEB benchmarks to fine-tune this model.
Márton