Instructions to use blackmount8/mpt-30b-instruct-ct2-int8_float16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use blackmount8/mpt-30b-instruct-ct2-int8_float16 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("blackmount8/mpt-30b-instruct-ct2-int8_float16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 793dd9a3edb08c94d340e40c7b381aae32bc05f7542d68f38f461667ffa2e5a5
- Size of remote file:
- 30 GB
- SHA256:
- 992a79c800728d5c6dc891e56e34ce7357b97d84b365fc8b4372d4fb5024c169
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.