Instructions to use TheBloke/MPT-7B-Instruct-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/MPT-7B-Instruct-GGML with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/MPT-7B-Instruct-GGML", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download mpt-7b-instruct.ggmlv3.fp16.bin from TheBloke/MPT-7B-Instruct-GGML: direct link, hf CLI and curl.
- Browser
- Download file 13.3 GB
-
https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML/resolve/main/mpt-7b-instruct.ggmlv3.fp16.bin
- Command line
-
hf download hf://TheBloke/MPT-7B-Instruct-GGML/mpt-7b-instruct.ggmlv3.fp16.bin
-
curl -L -o mpt-7b-instruct.ggmlv3.fp16.bin https://huggingface.co/TheBloke/MPT-7B-Instruct-GGML/resolve/main/mpt-7b-instruct.ggmlv3.fp16.bin
13.3 GB
- Xet hash:
- 58688a7aef1b32b13ebe1b0fcbede568f8ac557be5e5d9513b0d84fddcaa7cbf
- Size of remote file:
- 13.3 GB
- SHA256:
- a893f62683bcad46ce2c537bb6a1939298f7dca316a3ebb8fb879785fd9a1574
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.