Open s2t2 opened 10 months ago
To reduce costs, improve privacy, and accelerate development and testing, let's use an open source models instead of OpenAI models (for text embeddings, as well as for the LLM).
Consider using Llama.
"microsoft/phi-2" model from hugging face hub looks promising as well.
To reduce costs, improve privacy, and accelerate development and testing, let's use an open source models instead of OpenAI models (for text embeddings, as well as for the LLM).
Consider using Llama.