transformers调用llama的使用方式
llamatransformers_1">不同版本llama对应的transformers库版本
# llama2
pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
pip install transformers==4.32.1
pip install accelerate==0.22.0
# llama3
pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
pip install transformers==4.35.0
pip install accelerate==0.22.0
# llama3.1
pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu118
pip install transformers==4.43.1
pip install accelerate==0.22.0
llama2_17">llama2
待补充
llama3_19">llama3
Meta-Llama-3-8B-Instruct
可用于QA，summarize，示例代码
from transformers import AutoTokenizer, AutoModelForCausalLM
import torchmodel_id = "meta-llama/Meta-Llama-3-8B-Instruct"tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained
