南栖's repositories

character_AI_open

Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.

deepspeed-grpo-qlora-vllm

This repository, deepspeed-grpo-qlora-vllm, provides a complete framework for fine-tuning LLMs using Group Relative Policy Optimization (GRPO) on 4-bit quantized models (QLoRA). It utilizes DeepSpeed ZeRO-3 for scalable training and integrates with a VLLM server to dynamically serve the fine-tuned LoRA adapters.

Language:PythonLicense:Apache-2.0Stargazers:12Issues:0Issues:0

nBAT

BiLSTM-Attention Transformer for non-coding RNA Coding Potential Prediction(Code)Journal of Chemical Information and Modeling 2024-08-09 | Journal article DOI: 10.1021/acs.jcim.4c01097

Language:PythonStargazers:4Issues:1Issues:0

attention_sinks_autogptq

attention_sinks can use autogptq,and support all model at autogptq,like qwen baichuan,etc

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0

Infinite-Evolution-AI

Iteratively Generating Complex Evolutionary Networked Instructions uncensored.

Language:PythonStargazers:1Issues:1Issues:0
Language:PythonLicense:GPL-3.0Stargazers:1Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonStargazers:0Issues:0Issues:0

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:0Issues:0Issues:0

AutoGPTQ_cogvlm

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

Bert-VITS2

vits2 backbone with bert

Language:PythonLicense:AGPL-3.0Stargazers:0Issues:0Issues:0

character_AI_open_evol

Achieve 2–3× roleplay performance through LLM self-iteration with MCTS and evol instruction.

Stargazers:0Issues:0Issues:0

Emotional-ai

Emotional ai

Stargazers:0Issues:1Issues:0

InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

Language:PythonStargazers:0Issues:0Issues:0

wxbot

PC微信Hook模块、Hook WeChat / 微信逆向、微信机器人、WeChatRobot

Language:GoStargazers:0Issues:0Issues:0

Evol_Mctsr

Achieve a 2x-3x performance improvement through LLM self-iteration with MCTS and evo instruction.

Stargazers:0Issues:1Issues:0

hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

License:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0

MemAgent

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

mini-omni2

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

License:MITStargazers:0Issues:0Issues:0

nemori

A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

OpenAlita

Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Language:PythonStargazers:0Issues:0Issues:0

OpenAlpha_Evolve

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

License:MITStargazers:0Issues:0Issues:0

theLMbook

This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov

Language:Jupyter NotebookStargazers:0Issues:0Issues:0

titans

Titans paper implementation

Language:PythonStargazers:0Issues:0Issues:0

trl

Train transformer language models with reinforcement learning.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

vllm-gptq

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0