went through retrieval QA demo using multiple LLMs including
"HuggingFaceH4/zephyr-7b-beta"
"meta-llama/Llama-2-7b-chat-hf"
"mistralai/Mistral-7B-v0.1"
"databricks/dolly-v2-3b"
upgrade langchain to overcome the bug:
Inference initialization failed: The model has been loaded with accelerate and therefore cannot be moved to a specific device. Please discard the device argument when creating your pipeline object.`
went through retrieval QA demo using multiple LLMs including
upgrade langchain to overcome the bug: