hhnqqq / GemmaLongText

Related projects ⓘ

Alternatives and complementary repositories for GemmaLongText

• jiahe7ay / infini-mini-transformer
  This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…
  ☆52Updated 6 months ago
• liyucheng09 / llm-compressive
  Longitudinal Evaluation of LLMs via Data Compression
  ☆25Updated 5 months ago
• FlagOpen / Infinity-Instruct
  ☆37Updated 4 months ago
• cofe-ai / Mu-scaling
  Research without Re-search: Maximal Update Parametrization Yields Accurate Loss Prediction across Scales
  ☆30Updated last year
• OpenLMLab / scaling-rope
  code for Scaling Laws of RoPE-based Extrapolation
  ☆70Updated last year
• genggui001 / Megatron-DeepSpeed-Llama
  ☆82Updated last year
• RUCAIBox / QuantizedEmpirical
  ☆13Updated last year
• TemporaryLoRA / Temp-LoRA
  ☆89Updated 7 months ago
• zexuanqiu / CLongEval
  CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models
  ☆38Updated 8 months ago
• shaochenze / PatchTrain
  Code for paper "Patch-Level Training for Large Language Models"
  ☆67Updated 3 months ago
• SparkJiao / llama-pipeline-parallel
  A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…
  ☆48Updated last year
• alanshi / charset_mnbvc
  本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作
  ☆55Updated 3 weeks ago
• Outsider565 / LoRA-GA
  ☆149Updated 2 weeks ago
• beichao1314 / Open-Llama
  The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.
  ☆60Updated 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
  ☆43Updated 9 months ago
• princeton-nlp / CEPE
  [ACL 2024] Long-Context Language Modeling with Parallel Encodings
  ☆142Updated 4 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆53Updated 4 months ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆90Updated 9 months ago
• aplmikex / deduplication_mnbvc
  文本去重
  ☆67Updated 5 months ago
• IronBeliever / CaR
  Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
  ☆65Updated last month
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆127Updated 4 months ago
• Zheng0428 / COIG-Kun
  ☆34Updated 2 months ago
• keezen / ntk_alibi
  NTK scaled version of ALiBi position encoding in Transformer.
  ☆66Updated last year
• Ascend / AscendSpeed
  ☆74Updated 10 months ago
• nishiwen1214 / Benchmark-leakage-detection
  Official completion of “Training on the Benchmark Is Not All You Need”.
  ☆26Updated last month
• zhaochenyang20 / Prompt2Model-Self-Guide
  SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper
  ☆25Updated 5 months ago
• DAMO-NLP-SG / CLEX
  [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models
  ☆72Updated 7 months ago
• nengwp / Lion-vs-Adam
  Lion and Adam optimization comparison
  ☆56Updated last year
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆57Updated last year