llama2-7b-chat-ggml / requirements.txt
ffreemt
Fix concurrency_count to avoid OOM
e1bd529
raw
history blame
120 Bytes
ctransformers # ==0.2.10 0.2.13
transformers # ==4.30.2
# huggingface_hub
gradio
loguru
about-time
psutil
dl-hf-model