erax-ai
/

EraX-LLaMA3.1-8B-DeepSeekR1-MLA-MoE-Raw

Text Generation

Mixture of Experts

multihead_latent_attention

mixtured_of_experts

Model card Files Files and versions

EraX-LLaMA3.1-8B-DeepSeekR1-MLA-MoE-Raw / model.safetensors.index.json

Commit History

Upload LlamaDeepSeekForCausalLM

a8f55bb
verified

erax commited on Mar 6