Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
test model inference benchmark（ChatGLM2-6B，LLaMA2-7b-chat，Baichuan2-7B-chat）
deepspeed_baichuan2_7B_base
baichuan2-7b-chat-v1
A tool for normalizing bibtex with official info.
Measurement of aspect-level uncertainty based on Baichuan2-7B-Chat
#大语言模型#Official inference library for Mistral models
qwen-7b and qwen-14b finetuning
#自然语言处理#A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Finetune LLaMA-7B with Chinese instruction datasets
Fine-tune mistral-7B on 3090s, a100s, h100s
Tutorial on training, evaluating LLM, as well as utilizing RAG, Agent, Chain to build entertaining applications with LLMs.分享如何训练、评估LLMs，如何基于RAG、Agent、Chain构建有趣的LLMs应用。
Baichuan2代码的逐行解析版本，适合小白
#大语言模型#Official release of InternLM2.5 base and chat models. 1M context support
#自然语言处理#通义千问-7B（Qwen-7B） 是阿里云研发的通义千问大模型系列的70亿参数规模的模型
RAG (Retrievel Augmented Generation) implementation using the Mistral-7B-Instruct-v0.1
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
Command-line script for inferencing from models such as MPT-7B-Chat
The "vicuna-installation-guide" provides step-by-step instructions for installing and configuring Vicuna 13 and 7B
A Alpaca-7b replication no limitation and mutilingual finetuned instruction LLaMA LoRA
基于baichuan-7b的开源多模态大语言模型
Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型
