LMDeploy模型量化

studio-conda -t lmdeploy -o pytorch-2.1.2

conda activate lmdeploy

pip install lmdeploy[all]==0.3.0

ls /root/share/new_models/Shanghai_AI_Laboratory/

touch /root/pipeline_transformer.py

将以下内容复制粘贴进入pipeline_transformer.py。

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("/root/internlm2-chat-1_8b", trust_remote_code=True)

# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and cause OOM Error.
model = AutoModelForCausalLM.from_pretrained("/root/internlm2-chat-1_8b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()

inp = "hello"
print("[INPUT]", inp)
response, history = model.chat(tokenizer, inp, history=[])
print("[OUTPUT]", response)

inp = "please provide three suggestions about time management"
print("[INPUT]", inp)
response, history = model.chat(tokenizer, inp, history=history)
print("[OUTPUT]", response)

python /root/pipeline_transformer.py