Victor94-king/NLP__ManVictor

CSDN of ManVictor

23

14 commits

updated Mar 31, 2025

See the code

README

自然语言处理

本人简介: 曼彻斯特大学研究生,目前就职于北京某车企,专注于AI包括不限于NLP & CV技术,助力工业落地项目, 有合作或者比赛联系可以联系379530647@qq.com

本人C站主页 : 曼城周杰伦-CSDN博客

本项目主要是日常的有关于NLP基础的介绍 & 原理 & 面经 & 经验 & 框架 & 应用 , 欢迎补充。

序号类别项目名称简介地址
1原理N-gram每个词出现的概率只取决于前面n - 1个单词的
2原理word2vec词向量jmlr.csail.mit.edu/papers/volume3/bengio03a/bengio03a.pdf
3原理NPLM神经概率语言模型bengio03a.dvi (mit.edu)
4原理seq2seq端到端的神经网络Sequence to Sequence Learning with Neural Networks (arxiv.org)
5原理attention注意力机制 Attention Is All You Need (arxiv.org)
6模型架构Transformer变形金刚,大模型基础结构Attention Is All You Need (arxiv.org)
7模型架构GPTGPT-3GPT-3: Its Nature, Scope, Limits, and Consequences
8模型架构chatGPT如何让GPT - 》 chatGPTTraining language models to follow instructions with human feedback (arxiv.org)
9训练框架DeepSpeed微软推出的提供了一站式的快速以及大规模的训练及推理框架,目前使用最广泛的训练框架microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. (github.com)
10应用Openaiopenai接口ChatGPT
11模型架构BERT自编码器-唯一的架构,初期使用最广泛的语言模型BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arxiv.org)
12微调Lora目前广泛使用的微调技术,通过冻结模型而训练增加adapter,从而达到微调适配下游任务的目的LoRA: Low-Rank Adaptation of Large Language Models (arxiv.org)
13微调Ptuning_V1利用在下游任务中前置添加若干个可更新参数的虚拟[tokens] 所构成的模板prompt 再输入到文本中GPT Understands, Too (arxiv.org)
13微调Ptuning_V2在V1的基础上,通过构造训练一个少量参数的prompt-encoder(lstm+mlp) 构建无真实语义信息的 virtual token P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks (arxiv.org)
14推理框架Xinference性能强大且功能全面的分布式推理框架xorbitsai/inference: Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. (github.com)
15RAGnaive-RAG检索召回技术, 目前最主流减少大模型幻觉的落地技术Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (arxiv.org)
16RAGadvanced-RAG增强的检索召回技术思路
17RAGRAGASRAG性能评估框架explodinggradients/ragas: Supercharge Your LLM Application Evaluations 🚀 (github.com)
1w微调QLora量化版的Lora微调技术artidoro/qlora: QLoRA: Efficient Finetuning of Quantized LLMs (github.com)
19微调Lora & QLoralora & QLora 微调技巧lightning.ai/pages/community/tutorial/lora-llm/
20RAG框架Dify工业主流RAG & agent 框架部署指南langgenius/dify: Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. (github.com)
21模型架构LLama1META公司推出的SOTA 开源大模型https://arxiv.org/pdf/2302.13971.pdf
22模型架构LLama2META公司推出的SOTA 开源大模型2302.13971 (arxiv.org)
23模型架构Mistral 7BMistral AI公司推出的第一个基座大模型2401.04088 (arxiv.org)
24原理layerNorm为什么在NLP领域中普遍用LayerNorm 而不是BatchNorm
25微调SFT-trick微调技术的一些小技巧
26模型架构Mistral 8x7B第一个知名的MOE架构的大模型2401.04088 (arxiv.org)
27微调ParameterTrainingArguments参数设置
28模型架构LLama3META公司推出的SOTA 开源大模型meta-llama/llama3: The official Meta Llama 3 GitHub site
29应用gpt一些好用的gpt套壳网站
30微调trainertransformer.Trainer参数设置
31RAGadvanced-RAG优化的检索召回技术思路
32RAGHippoRAGHippoRAG结合了大型语言模型(LLMs)、知识图谱和个性化PageRank算法HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
33RAGFILCORAG过滤内容增强的RAG技术Learning to Filter Context for Retrieval-Augmented Generation (arxiv.org)
34微调lora VS finetuning到底是应该选择Lora还是选择全量微调? LoRA Learns Less and Forgets Less
35评测MTEBembedding模型性能评测榜单MTEB: Massive Text Embedding Benchmark (arxiv.org)](https://arxiv.org/abs/2210.07316)
36RAGHyKGERAG北大结合知识图谱的意料RAGHyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
37RAGRAFT该技术通过结合相关文档的检索和模型的微调,从而提升模型在特定领域内的推理能力RAFT: Adapting Language Model to Domain Specific RAG (arxiv.org)
38模型架构Timsfm专为时间序列预测设计的解码器通用大基础模型A decoder-only foundation model for time-series forecasting (arxiv.org)
39评测CEval全面评估中文环境下基础模型能力的解决方案2305.08322
40prompt工程prompt如何与大模型交流--prompt工程Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
41原理parameter解读大模型的参数
42RAGClashEval但当检索到的内容存在错误或有害信息时,模型会优先同意召回的信息而不是大模型本身信息ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence
43RAGVisualRAG视觉+RAGpipeline
45RAGGraphRAG微软开源的知识图谱+ RAGmicrosoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system
46RAGGraphRAGGraphRAG快速入门microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system
47微调prompt-tuningprompt tuing & instruction tuning & chain-of-though三者区别
48微调DDP分布式训练
49面经Lora面经Lora面经
50模型架构OLMoE第一个开源MOE大模型2409.02060
51面经langchain面经langchain面经
52RAGlongCite助力大模型找到长文本引用THUDM/LongCite: LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
53推理框架Ollama大模型部署框架ollama/ollama: Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
54训练框架Llama-factory一站式中文训练模型框架hiyouga/LLaMA-Factory: Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
55RAG框架FastGPTFastGPT 是一个基于 LLM 大语言模型的知识库问答系统,提供开箱即用的数据处理、模型调用等能力labring/FastGPT: FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
56面经RAGRAG面经
57原理RoPE旋转位置编码原理详解
58原理LLM从0->1构建自己的大模型如何从头训练大语言模型: A simple technical report - 知乎
59评测evaluateLLM评估指南如何从头训练大语言模型: A simple technical report - 知乎
60RAGtext2vec如何选择chunksize 和splitterHuixiangDou/README_zh.md at main · InternLM/HuixiangDou
61RAGembedding微调embedding
62RAGKAGKAG 旨在充分利用知识图谱和向量检索的优势,并通过四个方面双向增强大型语言模型和知识图谱,以解决 RAG 挑战OpenSPG/KAG: KAG is a knowledge-enhanced generation framework based on OpenSPG engine, which is used to build knowledge-enhanced rigorous decision-making and information retrieval knowledge services
63模型架构Qwen2阿里千问Qwen2系列QwenLM/Qwen2.5: Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
64模型架构Qwen2代码Qwen2代码解析
65文档解析MinerU免费精准解析PDF文档的开源解决方案
66prompt工程promptprompt 工程合辑
67prompt工程PromptimLangChain推出自动化提示优化工具Promptim:一键优化,效率倍增LangChain推出自动化提示优化工具Promptim:一键优化,效率倍增hinthornw/promptimizer: Prompt optimization scratch
68prompt工程De_Ai一键去除Ai味
69推理框架vllm大模型集群分部署部署框架
70LangchainLangchain_SummaryLangchain的长文本总结处理方式vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
71RAGTable_RAG表格RAG的处理方式command 'office.markdown.switch' not found
72RAGLazyGraphRAG微软重磅推出高性价比下一代GraphRAG
73RAGAdvanced_RAG十种提升RAG效果的方法
74RAGGraph_RAG深度解读GraphRAG(转载)
75RAGPDF利用LLM从非结构化PDF中提取结构化知识
76面经RoPE手写一下正弦编码和旋转位置编码的代码
77面经ScallingLawscalling law = 幂律?
78RAGRAGGraphRAG、Naive RAG框架总结主流框架推荐(共23个):LightRAG、nano-GraphRAG、Dify等GraphRAG、Naive RAG框架总结主流框架推荐(共23个):LightRAG、nano-GraphRAG、Dify等
79RAGAdvancedRAGRAG落地解决方案
80RAGRAG_ChunkRAG分块策略
81RAGGraphRAG_Milvus利用Milvus向量数据库,实现GraphRAG:主流方法(递归、jina-seg)+前沿推荐(Meta-chunking、Late chunking、SLM-SFT)
82面经GPU如何估算大模型显存
83prompt工程Prompt_templatePrompt格式的重要性
84RAGMarkdownMarkdown文档如何切分
85MultiModalQwen2VLQwen2VL 多模态模型实践
86面经Deepspeed_ZeRODeepspeed_ZeRO各阶段配置
87RAGMarkitDown微软开源MarkitDown,RAG文档解析就这么解决了~
88Function_CallingFunction_Calling_1如何生成Function Calling微调数据?
89Function_CallingFunction_Calling_2如何提升Function Calling准确性
90RAGJina_splitter使用Jina API进行语义切分MasteringRAG/split/03_jina_segment_api.ipynb at main · Steven-Luo/MasteringRAG
91训练框架Accelerate训练加速框架之Acclerate
92AgentChatBIChatBI实践分享
93推理框架Paramter文本生成策略(beam search/top-k/top-p/温度系数)
94训练框架PPOPPO与GRPO 通俗讲解
95推理框架QVcache为什么只有KV cache 没有Q cache
96RAGChatBotAI 智能客服机器人解决方案
97训练框架Distillation大模型蒸馏技术详解
98RAG框架Dify_FastGPTDify外接Fastgpt知识库,这套组合可以说封神了!【喂饭级教程】
99RAG框架Dify_RagFlowdify v1.0.1外挂ragflow知识库,确实可以封神了!【喂饭级教程】
100面经Words大模型领域常用名词解释(近100个)
101模型架构DeepSeek免费使用DeepSeek平台
102模型架构DeepSeeK_DeCoT如何去掉DeepSeek R1的思考过程
103推理框架DeepSeek_Prefill私有化部署DeepSeek等大模型的性能估计
104推理框架DeepSeek_DeCoT生产环境vLLM 部署 DeepSeek,如何调优,看这里
105RAGDeepSeek_RAG不要盲目再使用DeepSeek R1和QWQ这些推理模型做RAG了
106RAGChunkRAG常见13种分块策略大总结(一览表)
107RAGRAG_20252025年值得关注的21个RAG开源项目
108原理GGUF大模型使用Safetensors不好吗?为什么还有GGUF
109训练框架DeepSeek_finetuning单卡4090微调DeepSeek-R1-32B
110RAGDify_ParentsDify 分段模式中的父子模式
111
TodoRAGOpen Parse提取PDF文档文字、表格混排自动识别Filimoa/open-parse: Improved file parsing for LLM’s (github.com)

Contributors

Victor94-king

14 commits

Victor94-king/NLP__ManVictor

CSDN of ManVictor

23

14 commits

updated Mar 31, 2025

See the code

README

自然语言处理

本人简介: 曼彻斯特大学研究生,目前就职于北京某车企,专注于AI包括不限于NLP & CV技术,助力工业落地项目, 有合作或者比赛联系可以联系379530647@qq.com

本人C站主页 : 曼城周杰伦-CSDN博客

本项目主要是日常的有关于NLP基础的介绍 & 原理 & 面经 & 经验 & 框架 & 应用 , 欢迎补充。

序号类别项目名称简介地址
1原理N-gram每个词出现的概率只取决于前面n - 1个单词的
2原理word2vec词向量jmlr.csail.mit.edu/papers/volume3/bengio03a/bengio03a.pdf
3原理NPLM神经概率语言模型bengio03a.dvi (mit.edu)
4原理seq2seq端到端的神经网络Sequence to Sequence Learning with Neural Networks (arxiv.org)
5原理attention注意力机制 Attention Is All You Need (arxiv.org)
6模型架构Transformer变形金刚,大模型基础结构Attention Is All You Need (arxiv.org)
7模型架构GPTGPT-3GPT-3: Its Nature, Scope, Limits, and Consequences
8模型架构chatGPT如何让GPT - 》 chatGPTTraining language models to follow instructions with human feedback (arxiv.org)
9训练框架DeepSpeed微软推出的提供了一站式的快速以及大规模的训练及推理框架,目前使用最广泛的训练框架microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. (github.com)
10应用Openaiopenai接口ChatGPT
11模型架构BERT自编码器-唯一的架构,初期使用最广泛的语言模型BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arxiv.org)
12微调Lora目前广泛使用的微调技术,通过冻结模型而训练增加adapter,从而达到微调适配下游任务的目的LoRA: Low-Rank Adaptation of Large Language Models (arxiv.org)
13微调Ptuning_V1利用在下游任务中前置添加若干个可更新参数的虚拟[tokens] 所构成的模板prompt 再输入到文本中GPT Understands, Too (arxiv.org)
13微调Ptuning_V2在V1的基础上,通过构造训练一个少量参数的prompt-encoder(lstm+mlp) 构建无真实语义信息的 virtual token P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks (arxiv.org)
14推理框架Xinference性能强大且功能全面的分布式推理框架xorbitsai/inference: Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. (github.com)
15RAGnaive-RAG检索召回技术, 目前最主流减少大模型幻觉的落地技术Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (arxiv.org)
16RAGadvanced-RAG增强的检索召回技术思路
17RAGRAGASRAG性能评估框架explodinggradients/ragas: Supercharge Your LLM Application Evaluations 🚀 (github.com)
1w微调QLora量化版的Lora微调技术artidoro/qlora: QLoRA: Efficient Finetuning of Quantized LLMs (github.com)
19微调Lora & QLoralora & QLora 微调技巧lightning.ai/pages/community/tutorial/lora-llm/
20RAG框架Dify工业主流RAG & agent 框架部署指南langgenius/dify: Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. (github.com)
21模型架构LLama1META公司推出的SOTA 开源大模型https://arxiv.org/pdf/2302.13971.pdf
22模型架构LLama2META公司推出的SOTA 开源大模型2302.13971 (arxiv.org)
23模型架构Mistral 7BMistral AI公司推出的第一个基座大模型2401.04088 (arxiv.org)
24原理layerNorm为什么在NLP领域中普遍用LayerNorm 而不是BatchNorm
25微调SFT-trick微调技术的一些小技巧
26模型架构Mistral 8x7B第一个知名的MOE架构的大模型2401.04088 (arxiv.org)
27微调ParameterTrainingArguments参数设置
28模型架构LLama3META公司推出的SOTA 开源大模型meta-llama/llama3: The official Meta Llama 3 GitHub site
29应用gpt一些好用的gpt套壳网站
30微调trainertransformer.Trainer参数设置
31RAGadvanced-RAG优化的检索召回技术思路
32RAGHippoRAGHippoRAG结合了大型语言模型(LLMs)、知识图谱和个性化PageRank算法HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
33RAGFILCORAG过滤内容增强的RAG技术Learning to Filter Context for Retrieval-Augmented Generation (arxiv.org)
34微调lora VS finetuning到底是应该选择Lora还是选择全量微调? LoRA Learns Less and Forgets Less
35评测MTEBembedding模型性能评测榜单MTEB: Massive Text Embedding Benchmark (arxiv.org)](https://arxiv.org/abs/2210.07316)
36RAGHyKGERAG北大结合知识图谱的意料RAGHyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
37RAGRAFT该技术通过结合相关文档的检索和模型的微调,从而提升模型在特定领域内的推理能力RAFT: Adapting Language Model to Domain Specific RAG (arxiv.org)
38模型架构Timsfm专为时间序列预测设计的解码器通用大基础模型A decoder-only foundation model for time-series forecasting (arxiv.org)
39评测CEval全面评估中文环境下基础模型能力的解决方案2305.08322
40prompt工程prompt如何与大模型交流--prompt工程Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
41原理parameter解读大模型的参数
42RAGClashEval但当检索到的内容存在错误或有害信息时,模型会优先同意召回的信息而不是大模型本身信息ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence
43RAGVisualRAG视觉+RAGpipeline
45RAGGraphRAG微软开源的知识图谱+ RAGmicrosoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system
46RAGGraphRAGGraphRAG快速入门microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system
47微调prompt-tuningprompt tuing & instruction tuning & chain-of-though三者区别
48微调DDP分布式训练
49面经Lora面经Lora面经
50模型架构OLMoE第一个开源MOE大模型2409.02060
51面经langchain面经langchain面经
52RAGlongCite助力大模型找到长文本引用THUDM/LongCite: LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
53推理框架Ollama大模型部署框架ollama/ollama: Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
54训练框架Llama-factory一站式中文训练模型框架hiyouga/LLaMA-Factory: Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
55RAG框架FastGPTFastGPT 是一个基于 LLM 大语言模型的知识库问答系统,提供开箱即用的数据处理、模型调用等能力labring/FastGPT: FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
56面经RAGRAG面经
57原理RoPE旋转位置编码原理详解
58原理LLM从0->1构建自己的大模型如何从头训练大语言模型: A simple technical report - 知乎
59评测evaluateLLM评估指南如何从头训练大语言模型: A simple technical report - 知乎
60RAGtext2vec如何选择chunksize 和splitterHuixiangDou/README_zh.md at main · InternLM/HuixiangDou
61RAGembedding微调embedding
62RAGKAGKAG 旨在充分利用知识图谱和向量检索的优势,并通过四个方面双向增强大型语言模型和知识图谱,以解决 RAG 挑战OpenSPG/KAG: KAG is a knowledge-enhanced generation framework based on OpenSPG engine, which is used to build knowledge-enhanced rigorous decision-making and information retrieval knowledge services
63模型架构Qwen2阿里千问Qwen2系列QwenLM/Qwen2.5: Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
64模型架构Qwen2代码Qwen2代码解析
65文档解析MinerU免费精准解析PDF文档的开源解决方案
66prompt工程promptprompt 工程合辑
67prompt工程PromptimLangChain推出自动化提示优化工具Promptim:一键优化,效率倍增LangChain推出自动化提示优化工具Promptim:一键优化,效率倍增hinthornw/promptimizer: Prompt optimization scratch
68prompt工程De_Ai一键去除Ai味
69推理框架vllm大模型集群分部署部署框架
70LangchainLangchain_SummaryLangchain的长文本总结处理方式vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
71RAGTable_RAG表格RAG的处理方式command 'office.markdown.switch' not found
72RAGLazyGraphRAG微软重磅推出高性价比下一代GraphRAG
73RAGAdvanced_RAG十种提升RAG效果的方法
74RAGGraph_RAG深度解读GraphRAG(转载)
75RAGPDF利用LLM从非结构化PDF中提取结构化知识
76面经RoPE手写一下正弦编码和旋转位置编码的代码
77面经ScallingLawscalling law = 幂律?
78RAGRAGGraphRAG、Naive RAG框架总结主流框架推荐(共23个):LightRAG、nano-GraphRAG、Dify等GraphRAG、Naive RAG框架总结主流框架推荐(共23个):LightRAG、nano-GraphRAG、Dify等
79RAGAdvancedRAGRAG落地解决方案
80RAGRAG_ChunkRAG分块策略
81RAGGraphRAG_Milvus利用Milvus向量数据库,实现GraphRAG:主流方法(递归、jina-seg)+前沿推荐(Meta-chunking、Late chunking、SLM-SFT)
82面经GPU如何估算大模型显存
83prompt工程Prompt_templatePrompt格式的重要性
84RAGMarkdownMarkdown文档如何切分
85MultiModalQwen2VLQwen2VL 多模态模型实践
86面经Deepspeed_ZeRODeepspeed_ZeRO各阶段配置
87RAGMarkitDown微软开源MarkitDown,RAG文档解析就这么解决了~
88Function_CallingFunction_Calling_1如何生成Function Calling微调数据?
89Function_CallingFunction_Calling_2如何提升Function Calling准确性
90RAGJina_splitter使用Jina API进行语义切分MasteringRAG/split/03_jina_segment_api.ipynb at main · Steven-Luo/MasteringRAG
91训练框架Accelerate训练加速框架之Acclerate
92AgentChatBIChatBI实践分享
93推理框架Paramter文本生成策略(beam search/top-k/top-p/温度系数)
94训练框架PPOPPO与GRPO 通俗讲解
95推理框架QVcache为什么只有KV cache 没有Q cache
96RAGChatBotAI 智能客服机器人解决方案
97训练框架Distillation大模型蒸馏技术详解
98RAG框架Dify_FastGPTDify外接Fastgpt知识库,这套组合可以说封神了!【喂饭级教程】
99RAG框架Dify_RagFlowdify v1.0.1外挂ragflow知识库,确实可以封神了!【喂饭级教程】
100面经Words大模型领域常用名词解释(近100个)
101模型架构DeepSeek免费使用DeepSeek平台
102模型架构DeepSeeK_DeCoT如何去掉DeepSeek R1的思考过程
103推理框架DeepSeek_Prefill私有化部署DeepSeek等大模型的性能估计
104推理框架DeepSeek_DeCoT生产环境vLLM 部署 DeepSeek,如何调优,看这里
105RAGDeepSeek_RAG不要盲目再使用DeepSeek R1和QWQ这些推理模型做RAG了
106RAGChunkRAG常见13种分块策略大总结(一览表)
107RAGRAG_20252025年值得关注的21个RAG开源项目
108原理GGUF大模型使用Safetensors不好吗?为什么还有GGUF
109训练框架DeepSeek_finetuning单卡4090微调DeepSeek-R1-32B
110RAGDify_ParentsDify 分段模式中的父子模式
111
TodoRAGOpen Parse提取PDF文档文字、表格混排自动识别Filimoa/open-parse: Improved file parsing for LLM’s (github.com)

Contributors

Victor94-king

14 commits