Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.
GPL-3.0 License
🦖 X—LLM: Cutting Edge & Easy LLM Finetuning
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
本地部署大语言模型的中文教学
AirLLM 70B inference with single 4GB GPU
An open-source cloud-native of large multi-modal models (LMMs) serving framework.
A lightweight library that leverages Language Models (LLMs) to enable natural language interactio...
Finetune llama2-70b and codellama on MacBook Air without quantization
Run any Large Language Model behind a unified API
An OpenAI-like LLaMA inference API
Inference code for CodeLlama models
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable fo...
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델
GPT-4 level function calling models for real-world tool using use cases
开源社区第一个能下载、能运行的中文 LLaMA2 模型!
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and paramete...