模型:

ethzanalytics/stablelm-tuned-alpha-3b-sharded

英文

StableLM-Tuned-Alpha:分片检查点

这是模型的分片检查点(带有约2GB的分片)。有关所有详细信息,请参考 original model

基本用法

安装transformers,accelerate和bitsandbytes。

pip install -U -q transformers bitsandbytes accelerate

以8位加载模型,然后 run inference

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "ethzanalytics/stablelm-tuned-alpha-3b-sharded"
tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(model_name, load_in_8bit=True)