Feature Extraction
Transformers
ONNX
English
bert
mteb
sparse
sparsity
quantized
embeddings
int8
deepsparse
Eval Results (legacy)
Instructions to use RedHatAI/bge-base-en-v1.5-quant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/bge-base-en-v1.5-quant with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="RedHatAI/bge-base-en-v1.5-quant")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("RedHatAI/bge-base-en-v1.5-quant") model = AutoModel.from_pretrained("RedHatAI/bge-base-en-v1.5-quant") - Notebooks
- Google Colab
- Kaggle
Missing files
#1
by do-me - opened
Hey, great work! I love your mission of bringing LLMs to the GPU-poor but CPU-rich masses. I am on a similar mission: I would like to use your bge models in with transformers.js in SemanticFinder but I currently cannot load them due to the following missing files:
- special_tokens_map.json
- vocab.txt
- tokenizer_config.json
(also missing in sparse version)
Could you please add them?
Also, would you mind tagging all your onnx models with transformers.js too? I'm periodically mining all feature-extraction models so it would be cool if your models would then land in my data dump automatically. :)