Beam search generation
hellowoe23 opened this issue · comments
Has this project implemented a beam search method for generating a list of appropriate answers?
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
hellowoe23 opened this issue · comments
Has this project implemented a beam search method for generating a list of appropriate answers?