The community members are discussing loading the LLaMA 2 model using HuggingFaceLLM instead of Replicate, and trying to do this on Azure Databricks. One community member suggests a Discord link that might help, and another asks if they can directly pull the checkpoints with HuggingFaceLLM like model = 'meta-llama/Llama-2-13b-chat-hf', as shown in a provided link. A response indicates that as long as the community member has access from HuggingFace, they can create the model and tokenizer like the example and pass them as kwargs to the HuggingFace LLM, which will download the checkpoints automatically.
As long as you have access from huggingface, yea I think so
You can create the model and tokenzier like that example, and then pass them in as kwargs to the huggingface llm. The example in the link above will download them automatically
