Instructions to use kyutai/mimi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kyutai/mimi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="kyutai/mimi")# Load model directly from transformers import AutoFeatureExtractor, AutoModelForMultimodalLM extractor = AutoFeatureExtractor.from_pretrained("kyutai/mimi") model = AutoModelForMultimodalLM.from_pretrained("kyutai/mimi") - Inference
- Notebooks
- Google Colab
- Kaggle
Why the weight_norm has been removed
#4
by Xiaoyu94 - opened
Hi, I'm wondering why the weight_norm for each convolutional layer has been removed in the HuggingFace implementation (https://github.com/huggingface/transformers/blob/main/src/transformers/models/mimi/modeling_mimi.py#L213-L225)
while the official implementation kept it (https://github.com/kyutai-labs/moshi/blob/main/moshi/moshi/modules/conv.py#L126). If I understood well, HF has the code regarding weight_norm (https://github.com/huggingface/transformers/blob/main/src/transformers/models/mimi/modeling_mimi.py#L170-L178) but this code has never been used during forward()