Revisioni di GPT4All-2.py

1 file changed, 4 insertions

GPT4All-2.py(file creato)

		@@ -0,0 +1,4 @@
1	+	from gpt4all import GPT4All
2	+	model = GPT4All("Meta-Llama-3-8B-Instruct.Q4_0.gguf") # downloads / loads a 4.66GB LLM
3	+	with model.chat_session():
4	+	print(model.generate("How can I run LLMs efficiently on my laptop?", max_tokens=1024))

Più nuovi Più vecchi