RJ Adriaansen

FYI: I just submitted this pull request to integrate llama.cpp into langchain: https://github.com/hwchase17/langchain/pull/2242

I second this. I've been working on integrating llama.cpp in langchain, but the retrieval of embeddings is terribly slow since we can only pass [single strings](https://github.com/hwchase17/langchain/blob/master/langchain/embeddings/llamacpp.py#L111) (for which the model...

Do you get more meaningful output if you set the seed to random? `llm = Llama(model_path="ggml-model-q4_0-new.bin", seed=-1)`

I like the direction where this is headed, but I like alpaca's a magnitude more.

I'm not sure if we realize how much we're innovating poststructural semiotics here. This commit moves way beyond the deconstruction of LLMs' logocentrism. Linking the ultimate indeterminacy of meaning to...

Install this: `pip install git+https://github.com/boudinfl/pke.git`