Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs

Add code
Jul 16, 2024
Figure 1 for Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs
Figure 2 for Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs
Figure 3 for Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs
Figure 4 for Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: