LLaMA-MoE

https://github.com/pjlab-sys4nlp/llama-moe

AI & ML interests

None defined yet.

Recent Activity

tongjingqi authored a paper 16 days ago

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

tongjingqi authored a paper 16 days ago

Adaptive Fast-and-Slow Visual Program Reasoning for Long-Form VideoQA

tongjingqi authored a paper 16 days ago

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

View all activity

llama-moe 's models 8

llama-moe/LLaMA-MoE-v2-3_8B-residual-sft

8B • Updated Dec 3, 2024 • 6 • 2

llama-moe/LLaMA-MoE-v2-3_8B-2_8-sft

8B • Updated Dec 3, 2024 • 168 • 6

llama-moe/LLaMA-MoE-v1-3_0B-2_16

Text Generation • Updated Jun 25, 2024 • 779 • 11

llama-moe/LLaMA-MoE-v1-3_5B-4_16

Text Generation • Updated Jun 25, 2024 • 554 • 16

llama-moe/LLaMA-MoE-v1-3_0B-2_16-sft

Text Generation • 7B • Updated Jun 25, 2024 • 7 • 2

llama-moe/LLaMA-MoE-v1-3_5B-2_8-sft

Text Generation • 7B • Updated Jun 25, 2024 • 12 • 3

llama-moe/LLaMA-MoE-v1-3_5B-4_16-sft

Text Generation • 7B • Updated Jun 25, 2024 • 11 • 1

llama-moe/LLaMA-MoE-v1-3_5B-2_8

Text Generation • Updated Jun 25, 2024 • 1.23k • 15