Alternatives and similar repositories for Sparse_MultiLabel_Categorical_CrossEntropy

Users that are interested in Sparse_MultiLabel_Categorical_CrossEntropy are comparing it to the libraries listed below

• rucmlcv / Wenlan-Video-Public
  ☆19Updated 3 years ago
• RUC-AIMind / TikTalk
  ☆69Updated 3 weeks ago
• MUGE-2021 / image-generation-baseline
  ☆32Updated 2 years ago
• km1994 / nlp_paper_study_search_engine
  该仓库主要记录 NLP 算法工程师相关的 搜索引擎 学习笔记
  ☆13Updated 3 years ago
• zglxjtu / ATEC2023-Q1-Introduction-of-Large-Model-Knowledge
  ATEC2023——赛道一: 大模型的知识引入Rank7方案分享
  ☆22Updated 8 months ago
• billjie1 / Chinese-CLIP
  Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
  ☆168Updated 2 years ago
• keezen / ntk_alibi
  NTK scaled version of ALiBi position encoding in Transformer.
  ☆68Updated last year
• Lisennlp / distributed_train_pytorch
  pytorch分布式训练，支持多机多卡，单机多卡。
  ☆41Updated 3 years ago
• BAAI-WuDao / WuDaoMM
  WuDaoMM this is a data project
  ☆74Updated 3 years ago
• ssbuild / chatglm_rlhf
  chatglm_rlhf_finetuning
  ☆29Updated last year
• CLUEbenchmark / SuperCLUE-Math6
  SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅
  ☆56Updated last year
• lucasjinreal / LLaVA-Magvit2
  LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
  ☆37Updated last year
• thu-ml / zh-clip
  ☆68Updated 2 years ago
• yichengchen24 / MIG
  Official code for MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
  ☆20Updated last month
• zzy99 / My-competition-solutions
  我的数据竞赛方案总结
  ☆68Updated last year
• cjymz886 / LLM-RAG-QA
  LLM+RAG for QA
  ☆21Updated last year
• AI-confused / arxiv_auto_crawler
  auto scrawl for arrive data
  ☆15Updated 3 years ago
• QQ-MM / QQMM-embed
  ☆15Updated last month
• Decem-Y / sohu_text_matching_Rank2
  2021搜狐校园文本匹配算法大赛Top2方案
  ☆36Updated last year
• taishan1994 / Gector_chinese
  基于seq2edit (Gector) 的中文文本纠错。
  ☆28Updated 2 years ago
• menghuanlater / Tianchi2020ChineseMedicineNER
  2020阿里云天池大数据竞赛-中医药命名实体识别挑战赛
  ☆27Updated 4 years ago
• yanqiangmiffy / Product-Entity-Recognition
  商品标题实体识别
  ☆23Updated 3 years ago
• vxfla / kanchil
  Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。
  ☆113Updated 2 years ago
• MonolithFoundation / Bumblebee
  A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.
  ☆37Updated 9 months ago
• LydiaXiaohongLi / Megatron-DeepSpeed
  Ongoing research training transformer language models at scale, including: BERT & GPT-2
  ☆19Updated last year
• yuxie11 / R2D2
  ☆160Updated last year
• qychen2001 / Yaya-Moss-Alpaca-LoRA
  【丫丫】是以Moss作为基座模型，使用LoRA技术进行指令微调的尝试。由黄泓森，陈启源 @ 华中师范大学 主要完成。同时他也是【骆驼】开源中文大模型的一个子项目。
  ☆30Updated 2 years ago
• ZhuiyiTechnology / GAU-alpha
  基于Gated Attention Unit的Transformer模型（尝鲜版）
  ☆98Updated 2 years ago
• zejunwang1 / bloom_tuning
  BLOOM 模型的指令微调
  ☆24Updated 2 years ago
• CLUEbenchmark / SuperCLUE-Video
  中文原生多层次文生视频测评基准
  ☆17Updated 11 months ago