valkryhx

chatGLM-6B-QLoRA

lora_bnb_int8

利用LoRA bnb_int8微调chatYuan-large-v2的demo

-yolo3-on-win7-with-vs2015-opncv346

记录yolo3在win7 64位下的安装流程

ChatGLM-6B-api-update

ChatGLM-6B: api.py优化

ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

ChatGLM-LoRA-RLHF-PyTorch

A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM

ChatGLM-RLHF-LoRA-RM-PPO

ChatGLM-6B添加了RLHF的实现，以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Firefly

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)

Goat-Math-Chinese

山羊中文算术大模型

hierarchical-clustering-java

Implementation of an agglomerative hierarchical clustering algorithm in Java. Different linkage approaches are supported.

LightZero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios

LLaMA-Efficient-Tuning

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA)

LLM-Tuning

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

lora_bnb_ft_int8_chatYuan_large_v2

Fine-tuning_ChatYuan-largeV2_测试alpaca格式数据集_LoRA+bitsandbytes_int8微调_去掉全量finetune_保留int8模型加载测试_0415.ipynb

lora_bnb_int8_chatyuan

pytorch-YOLOv3-

tensorflow-2.0-

winutils

winutils.exe hadoop.dll and hdfs.dll binaries for hadoop windows

langchain_0831

⚡ Building applications with LLMs through composability ⚡

localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。

muzero-general

MuZero

Stochastic-muzero

Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.