<![CDATA[Raki_J的博客]]>https://blog.youkuaiyun.com/Raki_Jzh-cnhttps://blog.youkuaiyun.com/<![CDATA[Raki的读paper小记：GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints]]>https://blog.youkuaiyun.com/Raki_J/article/details/132199645https://blog.youkuaiyun.com/Raki_J/article/details/132199645Raki_JWed, 09 Aug 2023 23:20:40 +0800<![CDATA[Raki的读paper小记：RWKV: Reinventing RNNs for the Transformer Era]]>https://blog.youkuaiyun.com/Raki_J/article/details/132002725https://blog.youkuaiyun.com/Raki_J/article/details/132002725Raki_JSun, 30 Jul 2023 03:18:44 +0800<![CDATA[Raki的读paper小记：SELF-INSTRUCT: Aligning Language Models with Self-Generated Instructions]]>https://blog.youkuaiyun.com/Raki_J/article/details/131908503https://blog.youkuaiyun.com/Raki_J/article/details/131908503Raki_JThu, 27 Jul 2023 00:48:47 +0800<![CDATA[Raki的读paper小记：Retentive Network: A Successor to Transformer for Large Language Models]]>https://blog.youkuaiyun.com/Raki_J/article/details/131886803https://blog.youkuaiyun.com/Raki_J/article/details/131886803Raki_JMon, 24 Jul 2023 01:32:49 +0800<![CDATA[Raki的读paper小记：LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS]]>https://blog.youkuaiyun.com/Raki_J/article/details/131882188https://blog.youkuaiyun.com/Raki_J/article/details/131882188Raki_JSun, 23 Jul 2023 18:46:56 +0800<![CDATA[windows11安装pytorch2.0]]>https://blog.youkuaiyun.com/Raki_J/article/details/130208046https://blog.youkuaiyun.com/Raki_J/article/details/130208046Raki_JMon, 17 Apr 2023 20:34:06 +0800<![CDATA[思考AI科研的未来]]>https://blog.youkuaiyun.com/Raki_J/article/details/129996324https://blog.youkuaiyun.com/Raki_J/article/details/129996324Raki_JThu, 06 Apr 2023 19:20:27 +0800<![CDATA[近几年NLP比较promising的方法]]>https://blog.youkuaiyun.com/Raki_J/article/details/129736528https://blog.youkuaiyun.com/Raki_J/article/details/129736528Raki_JThu, 23 Mar 2023 19:33:45 +0800<![CDATA[Raki的读paper小记：Forget-free Continual Learning with Winning Subnetworks]]>https://blog.youkuaiyun.com/Raki_J/article/details/129346424https://blog.youkuaiyun.com/Raki_J/article/details/129346424Raki_JSun, 05 Mar 2023 22:43:42 +0800<![CDATA[Raki的读paper小记：Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Nets]]>https://blog.youkuaiyun.com/Raki_J/article/details/129329031https://blog.youkuaiyun.com/Raki_J/article/details/129329031Raki_JSat, 04 Mar 2023 16:29:36 +0800<![CDATA[Raki的读paper小记录：Online Continual Learning through Mutual Information Maximization]]>https://blog.youkuaiyun.com/Raki_J/article/details/129300301https://blog.youkuaiyun.com/Raki_J/article/details/129300301Raki_JFri, 03 Mar 2023 14:51:55 +0800<![CDATA[Transformer及其子孙后代]]>https://blog.youkuaiyun.com/Raki_J/article/details/129234304https://blog.youkuaiyun.com/Raki_J/article/details/129234304Raki_JWed, 01 Mar 2023 16:17:09 +0800<![CDATA[Raki的读paper小记：Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context]]>https://blog.youkuaiyun.com/Raki_J/article/details/129264037https://blog.youkuaiyun.com/Raki_J/article/details/129264037Raki_JTue, 28 Feb 2023 22:11:48 +0800<![CDATA[Raki的读paper小记：BART]]>https://blog.youkuaiyun.com/Raki_J/article/details/128678735https://blog.youkuaiyun.com/Raki_J/article/details/128678735Raki_JTue, 28 Feb 2023 01:24:12 +0800<![CDATA[Raki的读paper小记：ConTinTin: Continual Learning from Task Instructions]]>https://blog.youkuaiyun.com/Raki_J/article/details/128650845https://blog.youkuaiyun.com/Raki_J/article/details/128650845Raki_JThu, 12 Jan 2023 01:32:18 +0800<![CDATA[Raki的读paper小记：Continual Learning of Natural Language Processing Tasks: A Survey]]>https://blog.youkuaiyun.com/Raki_J/article/details/128572221https://blog.youkuaiyun.com/Raki_J/article/details/128572221Raki_JFri, 06 Jan 2023 19:27:06 +0800<![CDATA[Raki的读paper小记：An Image is Worth One Word Personalizing Text2Image using Textual Inversion]]>https://blog.youkuaiyun.com/Raki_J/article/details/127032505https://blog.youkuaiyun.com/Raki_J/article/details/127032505Raki_JSun, 25 Sep 2022 00:09:47 +0800<![CDATA[Raki的读paper小记：Image as a Foreign Language: BEIT Pretraining for All Vision and Vision-Language Tasks]]>https://blog.youkuaiyun.com/Raki_J/article/details/126514576https://blog.youkuaiyun.com/Raki_J/article/details/126514576Raki_JFri, 02 Sep 2022 20:19:31 +0800<![CDATA[Raki的读paper小记：CLIP:Learning Transferable Visual Models From Natural Language Supervision]]>https://blog.youkuaiyun.com/Raki_J/article/details/126666709https://blog.youkuaiyun.com/Raki_J/article/details/126666709Raki_JFri, 02 Sep 2022 17:30:32 +0800<![CDATA[Raki的读paper小记：ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision]]>https://blog.youkuaiyun.com/Raki_J/article/details/126664657https://blog.youkuaiyun.com/Raki_J/article/details/126664657Raki_JFri, 02 Sep 2022 16:14:28 +0800