Hi I'm using Jupyter Notebook, and trying to create instance of llama-2-7b-chat.q4_K_M.gguf (this is a quantized model) from hugging face. I'm running the following code:
from langchain_community.llms import CTransformers
llm = CTransformers(model="./models/llama-2-7b-chat.q4_K_M.gguf")
And when I run it my interface immediately says The kernel for Documents/llm_rcf/langchain_ctransformer_trial.ipynb appears to have died. It will restart automatically.
The terminal says the following :
[I 2024-04-16 11:58:17.119 ServerApp] AsyncIOLoopKernelRestarter: restarting kernel (1/5), keep random ports
[W 2024-04-16 11:58:17.120 ServerApp] kernel 7483deb0-17e0-4a4e-bce4-cc5f4d26fef9 restarted
[I 2024-04-16 11:58:17.134 ServerApp] Starting buffering for 7483deb0-17e0-4a4e-bce4-cc5f4d26fef9:18a4e018-29ef-47eb-8564-e33410b825af
[I 2024-04-16 11:58:17.195 ServerApp] Connecting to kernel 7483deb0-17e0-4a4e-bce4-cc5f4d26fef9.
[I 2024-04-16 11:58:17.196 ServerApp] Restoring connection for 7483deb0-17e0-4a4e-bce4-cc5f4d26fef9:18a4e018-29ef-47eb-8564-e33410b825af
[I 2024-04-16 11:58:26.144 ServerApp] Saving file at /Documents/llm_rcf/langchain_ctransformer_trial.ipynb
I have no idea whats going, would appreciate if anyone can help I'm using Apple's Mac Book Pro M1 Chip - 32 GB RAM and when I'm running it my activity monitor says Memory Used: 12.05GB, Physical Memory: 32.00GB