如何用pip安装kerasNLP的正确版本和内容？

Question

我的环境

• 操作系统：Windows 10
• python版本3.12.2
• 点 24.0
• 从未安装过tensorflow、keras或keras_nlp

我尝试按照此简介运行以下命令来安装 keras_nlp 和 keras。

pip install -U keras-nlp
pip install -U keras

命令运行成功。 但是我安装的kerasNLP似乎内容不正确，这里应该有很多模型。

这是我要测试的演示。

import keras_nlp
import os
os.environ["KERAS_BACKEND"] = "tensorflow"

gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("gemma_instruct_7b_en")
gotA = gemma_lm.generate("Keras is a", max_length=30)

print(gotA)

# Generate with batched prompts.
gotB = gemma_lm.generate(["Keras is a", "I want to say"], max_length=30)

print(gotB)

程序总是关闭并显示以下日志：

2024-02-25 23:23:39.045761: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-02-25 23:23:39.504814: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
Traceback (most recent call last):
  File "d:\llm_demo\gemma.py", line 5, in <module>
    gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("gemma_instruct_7b_en")
               ^^^^^^^^^^^^^^^^
AttributeError: module 'keras_nlp' has no attribute 'models'

我可以做些什么来让这个演示工作吗？

Answer 1

对我来说同样的错误。请建议该怎么做？