search

OpenThaiGPT / openthaigpt-pretraining

Apache License 2.0
21 stars 10 forks source link

Training test for LLaMa2 13B #279

Open ArthurMinovsky opened 1 year ago

ArthurMinovsky commented 1 year ago
boss-chanon commented 1 year ago

LLaMA2 13B can train in quantization 4 bit and sequence length 1024