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 10 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:
- 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
- 从预训练到强化学习的中文llama2☆88Updated last year
- ☆45Updated 2 months ago
- Official implementation of RARE: Retrieval-Augmented Reasoning Modeling☆171Updated last week
- 用VLLM框架部署千问1.5并进行流式输出☆89Updated last year
- Support mixed-precsion inference with vllm☆83Updated 4 months ago
- ☆130Updated 2 months ago
- SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL☆106Updated 2 weeks ago
- The framework to prune LLMs to any size and any config.☆92Updated last year
- Mixed precision inference by Tensorrt-LLM☆80Updated 7 months ago
- Chinese large language model☆120Updated last year
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆176Updated last month
- 教你只用最基本的python语法和numpy一步步实现深度学习框架☆128Updated 10 months ago
- Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.☆66Updated 10 months ago
- [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.☆167Updated 6 months ago
- Code and data for crosstalk text generation tasks, exploring whether large models and pre-trained language models can understand humor. …☆146Updated 2 years ago
- Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+…☆136Updated 3 weeks ago
- DeepRetrieval - 🔥 Training Search Agent with Retrieval Outcomes via Reinforcement Learning☆521Updated last week
- 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☆226Updated 2 months ago
- 最容易上手的0门槛 chatglm3 & agent & langchain 项目☆221Updated last year
- Train your Agent model via our easy and efficient framework☆776Updated last week
- A collection of papers related to knowledge fusion☆56Updated 7 months ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆175Updated 7 months ago
- Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasonin…☆168Updated 5 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆223Updated 8 months ago
- SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing☆143Updated 2 months ago
- Grimoire is All You Need for Enhancing Large Language Models☆115Updated last year
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆60Updated 7 months ago