cohere2

[kim90000]

from gpt4all import GPT4All
model = GPT4All("/content/c4ai-command-r7b-12-2024-abliterated-Q4_K_M.gguf") # downloads / loads a 4.66GB LLM
with model.chat_session():
print(model.generate("How can I run LLMs efficiently on my laptop?", max_tokens=1024))

RuntimeError: Unable to instantiate model: Unsupported model architecture: cohere2

[kim90000]

https://github.com/kim90000/c4ai-command-r7b-gguf/blob/main/c4ai_command_r7b%20(1).ipynb