hibikaze-git

LLaVA-JP

LLaVA-JP is a Japanese VLM trained by LLaVA method

ai_shrimin

create-data-for-vlm

ucllm_nedo_prod

dreamerv3

Mastering Diverse Domains through World Models

ExpeL

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

heron-llava-jp

To create V&L leaderboard with WandB

llm-jp-sft

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

pcae

[KBS] PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation PyTorch Implementation

vrchat-world-recommendation

whisper_mic

Project that allows one to use a microphone with OpenAI whisper.

scaling_on_scales

When do we not need larger vision models?

trl

Train transformer language models with reinforcement learning.