Taishi Nakamura's repositories
moe-recipes
Mixtre of Experts Library forked from kotoba-recipes
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
multimodal
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
llm-leaderboard
Project of llm evaluation to Japanese tasks
alignment-handbook
Robust recipes to align language models with human and AI preferences
long-context
YaRN: Efficient Context Window Extension of Large Language Models
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
SEED
Empowers LLMs with the ability to see and draw.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
mlmm-evaluation
Multilingual Large Language Models Evaluation Benchmark
llama-recipes
Examples and recipes for Llama 2 model
nccl-tests
NCCL Tests
rome
Locating and editing factual associations in GPT (NeurIPS 2022)
Megatron-LM-LUMI
Ongoing research training transformer models at scale
FIN-bench
Evaluation of Finnish generative models
Megatron-LLM
distributed trainer for LLMs