# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("microsoft/bloom-deepspeed-inference-int8")
model = AutoModel.from_pretrained("microsoft/bloom-deepspeed-inference-int8")Quick Links
This is a custom INT8 version of the original BLOOM weights to make it fast to use with the DeepSpeed-Inference engine which uses Tensor Parallelism. In this repo the tensors are split into 8 shards to target 8 GPUs.
The full BLOOM documentation is here.
To use the weights in repo, you can adapt to your needs the scripts found here (XXX: they are going to migrate soon to HF Transformers code base, so will need to update the link once moved).
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="microsoft/bloom-deepspeed-inference-int8")