Instructions to use naver/cocom-v1-128-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use naver/cocom-v1-128-mistral-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="naver/cocom-v1-128-mistral-7b", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("naver/cocom-v1-128-mistral-7b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
We need the version of the environment
There are many difficult-to-solve errors in the process of running inference. Can you show the versions of important packages such as Python, PyTorch, and Transformers? Thank you very much.
Hello,
Thank you for your interest into COCOM models.
They are deprecated in favor of the stronger PISCO models for which I'll gladly help if needed: https://huggingface.co/naver/pisco-mistral
Best,
Maxime
Thank you very much for your quick response, we need to cite cocom and do some experiments. We don't know how pisco is related to cocom. Are they essentially the same thing or is pisco a completely new work, how should we cite it.
Pisco paper is here https://arxiv.org/pdf/2501.16075
Pisco uses same architecture (but not same code) as cocom, but the models are trained by distillation which makes them susbstantially stronger. If you refer do table 2 you'll see the comparison.
Just in case, Oscar is also an interesting baseline (it's a query-dependent faster pisco/cocom): https://arxiv.org/abs/2504.07109
Thanks a lot!