huziyuan14 Goto Github PK

adapter-bert

alpaca-cot

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. Meanwhile, we created a new branch to build a Tabular LLM.（我们分别统一了丰富的IFT数据（如CoT数据，目前仍不断扩充）、多种训练效率方法（如lora，p-tuning）以及多种LLMs，三个层面上的接口，打造方便研究人员上手的LLM-IFT研究平台。同时tabular_llm分支构建了面向表格智能任务的LLM。

alpaca-lora

Instruct-tune LLaMA on consumer hardware

belle

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

bookcorpus

Crawl BookCorpus

chatglm-6b-qlora

使用peft库，对chatGLM-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

chatglm-tuning

一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA

chatgpt-corpus

ChatGPT 中文语料库 对话语料 小说语料 客服语料 用于训练大模型

chatlm-mini-chinese

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

chinese-medical-entity-recognition

Using BERT+Bi-LSTM+CRF

chinesenlpcorpus

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

cluedatasetsearch

搜索所有中文NLP数据集，附常用英文NLP数据集

colossalai

Making large AI models cheaper, faster and more accessible

ctr_prediction

CTR prediction using FM FFM and DeepFM

fastchat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

fb_client

fb_client

fb_server

fb_server

hugging-multi-agent

A tutorial based on MetaGPT to quickly help you understand the concept of agent and muti-agent and get started with coding development

jsgf-gen

Tool for generating tagged sentences from JSGF grammars

knowlm

Knowledgable Large Language Model Framework.

lexiconaugmentedner

Reject complicated operations for incorporating lexicon for Chinese NER.

linly

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

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.

llama-efficient-tuning

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen)

llm-sft

中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微调, 推理, 测评, 接口)等.

llm-tuning

Tuning LLMs with no tears💦, sharing LLM-tools with love❤️.

nlp

NLP相关源码

nlp2

Some application models of natural language processing

phi2-mini-chinese

Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.