okoge-kaz / moe-recipesLinks
Ongoing research training Mixture of Expert models.
☆21Updated last year
Alternatives and similar repositories for moe-recipes
Users that are interested in moe-recipes are comparing it to the libraries listed below
Sorting:
- Swallowプロジェクト 大規模言語モデル 評価スクリプト☆22Updated last month
- Japanese LLaMa experiment☆54Updated 10 months ago
- 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☆21Updated last month
- Mixtral-based Ja-En (En-Ja) Translation model☆19Updated 9 months ago
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆33Updated last year
- ☆62Updated last year
- LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation☆22Updated last year
- ☆33Updated last year
- ☆50Updated last year
- ☆42Updated last year
- The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.☆123Updated last week
- Project of llm evaluation to Japanese tasks☆90Updated 2 weeks ago
- ☆22Updated 2 years ago
- 日本語マルチタスク言語理解ベンチマーク Japanese Massive Multitask Language Understanding Benchmark☆36Updated last week
- Flexible evaluation tool for language models☆52Updated last week
- Easily turn large English text datasets into Japanese text datasets using open LLMs.☆22Updated 9 months ago
- ☆17Updated 3 weeks ago
- ☆138Updated this week
- Mamba training library developed by kotoba technologies☆70Updated last year
- Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"☆116Updated last week
- ☆18Updated 10 months ago
- ☆27Updated 11 months ago
- Ongoing Research Project for continaual pre-training LLM(dense mode)☆42Updated 7 months ago
- ☆14Updated last year
- Preferred Generation Benchmark☆85Updated last month
- ☆49Updated 10 months ago
- ☆14Updated last year
- Unofficial entropix impl for Gemma2 and Llama and Qwen2 and Mistral☆17Updated 9 months ago
- LLM構築用の日本語チャットデータセット☆86Updated last year
- Japanese-BPEEncoder☆41Updated 4 years ago