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 11 months ago
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:
- 从预训练到强化学习的中文llama2☆88Updated last year
- 用VLLM框架部署千问1.5并进行流式输出☆89Updated last year
- 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
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated last year
- GraphRAG-Bench, the official repo of comprehensive benchmark and dataset for evaluating GraphRAG models.☆88Updated this week
- ☆45Updated 2 months ago
- Support mixed-precsion inference with vllm☆84Updated 5 months ago
- The framework to prune LLMs to any size and any config.☆93Updated last year
- Official implementation of RARE: Retrieval-Augmented Reasoning Modeling☆181Updated 3 weeks ago
- SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL☆185Updated last month
- ☆54Updated last week
- Chinese large language model☆121Updated last year
- [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.☆167Updated 2 weeks ago
- Mixed precision inference by Tensorrt-LLM☆80Updated 8 months ago
- ☆139Updated 3 months ago
- [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models☆258Updated 3 months ago
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆178Updated 2 months 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 10 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。☆43Updated last year
- ✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork☆231Updated 2 weeks ago
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆42Updated last week
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆61Updated 8 months ago
- Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.☆66Updated 10 months ago
- A collection of papers related to knowledge fusion☆56Updated 8 months ago
- (ACL-2025 main conference) SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automat…☆249Updated 3 weeks ago
- [EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models☆70Updated 2 weeks ago
- 最容易上手的0门槛 chatglm3 & agent & langchain 项目☆221Updated last year
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆176Updated 7 months ago
- adds Sequence Parallelism into LLaMA-Factory☆518Updated last week
- Codebase for Iterative DPO Using Rule-based Rewards☆247Updated 2 months ago