wei-potato / Train-llm-from-scratchLinks
使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力
☆154Updated last month
Alternatives and similar repositories for Train-llm-from-scratch
Users that are interested in Train-llm-from-scratch are comparing it to the libraries listed below
Sorting:
- Official implementation of RARE: Retrieval-Augmented Reasoning Modeling☆183Updated 3 months ago
- This is a repo for my NanoGPT Pytorch2.0 Implementation when torch2.0 released soon, faster and simpler, a good tutorial learning GPT.☆52Updated last year
- ☆148Updated 6 months ago
- 用VLLM框架部署千问1.5并进行流式输出☆89Updated last year
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated last year
- 从预训练到强化学习的中文llama2☆87Updated last year
- [ACL 2025 Best Theme Paper] This is the official implementation for the paper: "Meta-rater: A Multi-dimensional Data Selection Method for…☆173Updated 2 weeks ago
- Search and Refine During Think: Autonomous Retrieval‑Augmented Reasoning of LLMs☆97Updated 3 weeks ago
- SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL☆191Updated 3 months ago
- Mixed precision inference by Tensorrt-LLM☆80Updated 10 months ago
- Support mixed-precsion inference with vllm☆84Updated 2 months ago
- Chinese large language model☆122Updated 2 years ago
- 教你只用最基本的python语法和numpy一步步实现深度学习框架☆129Updated last year
- The framework to prune LLMs to any size and any config.☆94Updated last year
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆68Updated 2 months ago
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆177Updated 5 months ago
- A scalable, end-to-end training pipeline for general-purpose agents☆359Updated 2 months ago
- 本项目旨在结合以往研究人员的代表性工作，从多个维度评估sft数据，并自动化过滤sft数据。☆44Updated last year
- Chat-Style-Bot是一个聊天风格模仿大语言模型，通过分析和学习微信聊天记录，可模仿你的说话风格（口头禅等），并可接入微信和你的朋友们自动聊天。Chat-Style-Bot is a chat style imitating llm. By analyzing an…☆113Updated last year
- 保险行业回访外呼机器人☆62Updated 2 years ago
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆62Updated 11 months ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆178Updated 10 months ago
- Code and data for crosstalk text generation tasks, exploring whether large models and pre-trained language models can understand humor. …☆147Updated 3 years ago
- This repository contains the core implementation of our ICML 2025 paper: "Token Signature: Predicting Chain-of-Thought Gains with Token D…☆41Updated last month
- Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.☆66Updated last year
- A collection of papers related to knowledge fusion☆59Updated 11 months ago
- [ACL2024 Findings] Towards Better Question Generation in QA-based Event Extraction☆47Updated 3 weeks ago
- Collecting personality-indicative data for role-playing agents.☆23Updated 6 months ago
- A library for generating difficulty-scalable, multi-tool, and verifiable agentic tasks with execution trajectories.☆162Updated 2 months ago
- Grimoire is All You Need for Enhancing Large Language Models☆117Updated last year