jackaduma / awesome_NLP-Interview-Notes
nlp_interview notes and answers: 该仓库主要记录 NLP 算法工程师相关的面试题和参考答案
☆20Updated last year
Alternatives and similar repositories for awesome_NLP-Interview-Notes:
Users that are interested in awesome_NLP-Interview-Notes are comparing it to the libraries listed below
- 大模型基础学习和面试八股文☆79Updated 10 months ago
- RAG 论文学习☆40Updated last week
- ☆128Updated 9 months ago
- A collection for math word problem (MWP) works, including datasets, algorithms and so on.☆39Updated 7 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆109Updated last year
- A paper & resource list of large language models, including course, paper, demo, figures☆195Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆73Updated 2 months ago
- basic framework for rag(retrieval augment generation)☆81Updated last year
- Real-time updated, fine-grained reading list on LLM-synthetic-data.🔥☆201Updated this week
- 此项目完成了关于 NLP-Beginner：自然语言处理入门练习 的所有任务（文本分类、信息抽取、知识图谱、机器翻译、问答系统、文本生成、Text-to-SQL、文本纠错、文本挖掘、知识蒸馏、模型加速、OCR、TTS、Prompt、embedding等），所有代码都经过测试…☆183Updated last year
- ☆120Updated 11 months ago
- 欢迎来到 "LLM-travel" 仓库！探索大语言模型（LLM）的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆287Updated 6 months ago
- ☆64Updated last year
- baichuan LLM surpervised finetune by lora☆61Updated last year
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆57Updated 7 months ago
- pytorch分布式训练☆63Updated last year
- 使用单个24G显卡，从0开始训练LLM☆50Updated 3 months ago
- ☆96Updated 2 months ago
- 怎么训练一个LLM分词器☆138Updated last year
- ☆98Updated 7 months ago
- 大语言模型应用：RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆53Updated last month
- 受到self-instruct启发,除了通用LLM还能做垂直领域的小LLM实现定制效果，通过GPT获得question和answer来作为训练数据☆14Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆333Updated 4 months ago
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆206Updated last year
- 一些 LLM 方面的从零复现笔记☆161Updated 4 months ago
- ☆161Updated last year
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆150Updated 3 months ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆75Updated 6 months ago
- 包含程序员面试大厂面试题和面试经验☆116Updated last month
- ☆78Updated last year