LLama3Rag / config.yaml
hanzla's picture
testing with llama2
77a3002
raw
history blame contribute delete
158 Bytes
modelEmbeddings: "sentence-transformers/all-MiniLM-L6-v2"
autoTokenizer: "meta-llama/Llama-2-7b-chat-hf"
autoModelForCausalLM: "meta-llama/Llama-2-7b-chat-hf"