Financial-Intent-Understanding-with-LLMs

AirLLM 70B inference with single 4GB GPU

Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.

[ACL 2024] Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models

This repo introduces MagicData-CLAM, a Chinese SFT dataset, and provides to the community two relevant models that we finetuned. Contact business@magicdatatech.com for more information.

LLM API Server , OpenAI 同时支持 ChatGLM3 ，Llama, Llama-3, Firefunction, Openfunctions ，BAAI/bge-m3 ,bge-large-zh-v1.5

大语言模型高效微调