Alternatives and similar repositories for jax-llm

Users that are interested in jax-llm are comparing it to the libraries listed below

• KanHatakeyama / synthetic-texts-by-llm
  ☆27Updated last year
• llm-jp / text2dataset
  Easily turn large English text datasets into Japanese text datasets using open LLMs.
  ☆24Updated 10 months ago
• swallow-llm / swallow-evaluation-instruct
  Swallowプロジェクト 事後学習済み大規模言語モデル 評価フレームワーク
  ☆23Updated last month
• nu-dialogue / jmultiwoz
  JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset, LREC-COLING 2024
  ☆25Updated last year
• pfnet-research / pfgen-bench
  Preferred Generation Benchmark
  ☆85Updated 3 weeks ago
• sbintuitions / JMTEB
  The evaluation scripts of JMTEB (Japanese Massive Text Embedding Benchmark)
  ☆74Updated last week
• GENZITSU / UsefulMaterials
  ☆34Updated 6 years ago
• hppRC / bert-classification-tutorial-2024
  【2024年版】BERTによるテキスト分類
  ☆30Updated last year
• swallow-llm / swallow-evaluation
  Swallowプロジェクト 大規模言語モデル 評価スクリプト
  ☆22Updated 2 months ago
• kunishou / databricks-dolly-15k-ja
  ☆88Updated 2 years ago
• hppRC / llm-translator
  Mixtral-based Ja-En (En-Ja) Translation model
  ☆20Updated 10 months ago
• SakanaAI / TAID
  Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"
  ☆118Updated last month
• megagonlabs / instruction_ja
  Japanese instruction data (日本語指示データ)
  ☆24Updated 2 years ago
• tanreinama / Japanese-BPEEncoder
  Japanese-BPEEncoder
  ☆41Updated 4 years ago
• megagonlabs / vecscan
  ☆51Updated 2 years ago
• hppRC / simple-simcse-ja
  Exploring Japanese SimCSE
  ☆69Updated 2 years ago
• kajyuuen / daaja
  This repository has implementations of data augmentation for NLP for Japanese.
  ☆64Updated 2 years ago
• CyberAgentAILab / minituna
  A toy hyperparameter optimization framework intended for understanding Optuna's internal design.
  ☆85Updated 4 years ago
• llm-jp / llm-jp-eval
  ☆140Updated last week
• daac-tools / python-vibrato
  Viterbi-based accelerated tokenizer (Python wrapper)
  ☆43Updated last year
• llm-jp / llm-jp-judge
  生成自動評価を行うためのPythonツール
  ☆32Updated last week
• line / LINE-DistilBERT-Japanese
  DistilBERT model pre-trained on 131 GB of Japanese web text. The teacher model is BERT-base that built in-house at LINE.
  ☆45Updated 2 years ago
• nobu-g / JGLUE-evaluation-scripts
  Training and evaluation scripts for JGLUE, a Japanese language understanding benchmark
  ☆17Updated 2 weeks ago
• yoheikikuta / support-genAI-book
  原論文から解き明かす生成AI（技術評論社）のサポートページです
  ☆78Updated 3 weeks ago
• Hajime-Y / reasoning-model
  ☆49Updated 11 months ago
• p-geon / ja-tokenizer-docker-py
  Mecab + NEologd + Docker + Python3
  ☆36Updated 3 years ago
• daac-tools / python-vaporetto
  🛥 Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto.
  ☆20Updated 5 months ago
• cl-tohoku / keigo_transfer_task
  敬語変換タスクにおける評価用データセット
  ☆21Updated 2 years ago
• ku-nlp / ja-vicuna-qa-benchmark
  ☆33Updated last year
• moisutsu / classopt
  Arguments parser with class for Python, inspired by StructOpt
  ☆61Updated 2 years ago