This model is based on bigscience/bloom-7b1.
We pruned its vocabulary from 250880 to 46145 with Chinese corpus to reduce GPU memory usage. So the total parameter is 6b4 now.
How to use
from transformers import BloomTokenizerFast, BloomForCausalLM
tokenizer = BloomTokenizerFast.from_pretrained('Langboat/bloom-6b4-zh')
model = BloomForCausalLM.from_pretrained('Langboat/bloom-6b4-zh')
print(tokenizer.batch_decode(model.generate(tokenizer.encode('中国的首都是', return_tensors='pt'))))
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.