Instructions to use sadmN/moshi-base7b-rag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use sadmN/moshi-base7b-rag with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "sadmN/moshi-base7b-rag" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("sadmN/moshi-base7b-rag") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes) - Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
Upload ckpt/rag_base7b/step_1500/student.pt with huggingface_hub
Verified signaturefccbd52 -
Upload moshi_base7b_server.zip with huggingface_hub
Verified signature08cf946 -
Upload download_assets.sh with huggingface_hub
Verified signaturede4ee0e -
Upload serve_base7b.sh with huggingface_hub
Verified signature3a5c05f -
Upload requirements-server.txt with huggingface_hub
Verified signatureb7e8de2 -
Upload setup_env.sh with huggingface_hub
Verified signatureaad9851 -
Upload README.md with huggingface_hub
Verified signature9dcb758 -
Upload rag_index_dense/meta.json with huggingface_hub
Verified signatureec68655 -
Upload rag_index_dense/emb.npy with huggingface_hub
Verified signature79dac6a -
Upload rag_index_dense/passages.jsonl with huggingface_hub
Verified signature8faab2d -
Upload tokenizer.model with huggingface_hub
Verified signatureacbf38f -
initial commit
Verified signaturea89340e