Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
lit-llama
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.
Repos like https://github.com/tloen/alpaca-lora and https://github.com/Lightning-AI/lit-llama use LoRA as a method to fine-tune LLaMA models.
Recently, I have seen the LoRA technique (Low-Rank Adaptation of Large Language Models) as a popular method for fine-tuning LLMs and other models.
Repos like https://github.com/tloen/alpaca-lora and https://github.com/Lightning-AI/lit-llama use LoRA as a method to fine-tune LLaMA models.
Hey! I am actually trying that task, with a little success. Trying to adapt MPT by mosaicML for Japanese. Someone has done similar things with LLama model (https://github.com/masa3141/japanese-alpaca-lora) . But I want to try with MPT model, however as you stated, the performance is quite not satisfactory. But the LLama model trained on Japanese alpaca seems to work fine!