https://www.nomic.ai/gpt4all

pip install gpt4all

from gpt4all import GPT4Allmodel = GPT4All("Meta-Llama-3-8B-Instruct.Q4_0.gguf") # downloads / loads a 4.66GB LLMwith model.chat_session():print(model.generate("How can I run LLMs efficiently on my laptop?", max_tokens=1024))

# 下载 GPT4All 模型并将其放置在您想要的目录中https://www.nomic.ai/gpt4all

from langchain_community.llms import GPT4All
# Instantiate the model. Callbacks support token-wise streamingmodel = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
# Generate textresponse = model.invoke("Once upon a time, ")

from langchain_community.llms import GPT4Allfrom langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
# There are many CallbackHandlers supported, such as# from langchain.callbacks.streamlit import StreamlitCallbackHandler
callbacks = [StreamingStdOutCallbackHandler()]model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
# Generate text. Tokens are streamed through the callback manager.model.invoke("Once upon a time, ", callbacks=callbacks)

https://github.com/nomic-ai/gpt4all