contenteaseAI/LargeLanguageModel

added spaces

removed spaces

modified the gpu , to stay within the limit

modified the chunk limit and added error handing and caching of the model

added chunks if tokens are more

added rag implementation for the model and specified a sys prompt

enabled error reporting

modified the prompt

changed the model

changed MODEL TO meta-llama-8b

modified the model and added template

changed meta-llama-8b

using zephyr model

initial commit

initial commit