-
final model (pool59k/top_k/air_eap_correctness/bottom)
-
final model (pool59k/top_k/air_eap_correctness/top)
-
final model (sweep_15ep/air_eap_correctness/top)
-
final model (sweep_15ep/air_eap_correctness/bottom)
-
final model (sweep_15ep/air_eap_correctness/middle)
-
final model (pool59k/top_k/base_loss/bottom)
-
final model (pool59k/top_k/base_loss/top)
-
final model (pool59k/top_k/air_retrieval/bottom)
-
final model (pool59k/top_k/air_retrieval/top)
-
final model (sweep_15ep/skill_coverage/middle)
-
final model (sweep_15ep/ifd/middle)
-
final model (sweep_15ep/skill_count/middle)
-
final model (sweep_15ep/response_length/middle)
-
final model (sweep_15ep/base_logprob_mean/middle)
-
final model (sweep_15ep/air_eap/middle)
-
final model (sweep_15ep/skill_coverage/bottom)
-
final model (sweep_15ep/skill_coverage/top)
-
final model (sweep_15ep/base_loss/bottom)
-
final model (sweep_15ep/base_loss/middle)
-
final model (sweep_15ep/base_loss/top)
-
final model (sweep_15ep/air_retrieval/bottom)
-
final model (sweep_15ep/air_retrieval/middle)
-
final model (sweep_15ep/air_retrieval/top)
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
final model (pool59k/top_k/ifd/bottom)
-
final model (pool59k/s1div/ifd/bottom)
-
final model (pool59k/s1div/ifd/top)
-
final model (pool59k/s1div/air_eap/bottom)
-
final model (pool59k/s1div/air_eap/top)
-
final model (sweep_15ep/skill_count/bottom)
-
final model (sweep_15ep/skill_count/top)
-
final model (sweep_15ep/response_length/bottom)
-
final model (sweep_15ep/base_logprob_mean/bottom)
-
final model (sweep_15ep/response_length/top)
-
final model (sweep_15ep/base_logprob_mean/top)
-
final model (screen/skill_count/middle)
-
final model (sweep_15ep/air_eap/bottom)
-
final model (sweep_15ep/air_eap/top)
-
final model (sweep_15ep/random/c_n334)
-
final model (sweep_15ep/ifd/bottom)
-
final model (sweep_15ep/ifd/top)
-
final model (sweep_15ep/random/b_n333)
-
final model (sweep_15ep/random/n333)
-
final model (full_runs/full_1k_5ep)
-
final model (screen/air_eap/bottom)
-
final model (screen/air_eap/middle)
-
final model (screen/air_eap/top)
-
final model (screen/air_retrieval/bottom)