add_eos_token_when_padded v. main
add_eos_token_when_padded
@f219302/Ensure trailing EOS token is added also when the generated output contains trailing padding as is often the case when doing batch generation/2023-04-05
main
@d7225c2/set torch dependency to version 2.0.0 for CUDA in installation instructions (#409)/2023-04-05
Created on April 5|Last edited on April 5
Comment
ppo_hh/gpt-j-6B/7gpus
ilql_randomwalks/GPT2Config/1gpu
ppo_hh/pythia-6B-static-sft/7gpus
sft_sentiments/gpt2/1gpu
ppo_sentiments_t5/t5-imdb/1gpu
ilql_sentiments/gpt2/1gpu
ppo_sentiments/gpt2-imdb/1gpu
ppo_randomwalks/randomwalks/1gpu
Add a comment