Text Generation
Transformers
PyTorch
Safetensors
English
llama
finance
text-generation-inference
Inference Endpoints

Good idea but why llama 1?

#1
by Delcos - opened

Why llama 1? Why not 2 or mistral?

Hi, thanks for your attention! This is mainly for research purpose. Our research, started at about April, way before LLaMA-2 and Mistral came into the scene. Back then we utilized LLaMA-1-7B for our investigations. As our work progressed, we conducted experiments on LLaMA-1-13B to assess the generalizability of our method to larger models. You may refer to our chat model at AdaptLLM/finance-chat to see the effectiveness of our method on LLaMA-2-Chat. And of course Mistral is part of our future plans, so please stay tuned!

Sign up or log in to comment