Jennny/new_data_sft_dpo_qwen25_1head_overall_values_5e7_2ep_bz192_9984
Updated
Jenny Shen PRO
Jennny
·
AI & ML interests
None yet
Recent Activity
new activity about 2 months ago
Jennny/qwen-math-value-model-join-09-5e5-3ep:Add model card and metadata new activity about 2 months ago
Jennny/llama3_8b_helpful_rm_full:Link model to paper and repository, add pipeline tag new activity about 2 months ago
Jennny/llama3_8b_honest_rm_full:Improve model card: add paper and code links, define model taskOrganizations
Jennny/new_init_sft_mdpo_qwen25_fsdp_5e7_2ep_bz128_acc_eng_14976
Updated
Jennny/new_init_sft_mdpo_qwen25_fsdp_5e7_2ep_bz128_acc_eng_9884
Updated
Jennny/new_init_sft_mdpo_qwen25_fsdp_5e7_2ep_bz128_acc_eng_4992
Updated
Jennny/new_sft_mdpo_qwen25_fsdp_5e7_2ep_bz128_acc_eng_12480
Updated
Jennny/new_sft_mdpo_qwen25_fsdp_5e7_2ep_bz128_acc_eng_LATEST
Updated
Jennny/new_sft_mdpo_qwen25_fsdp_5e7_1ep_bz128_acc_eng_LATEST
Updated
Jennny/new_sft_dpo_qwen25_1head_overall_values_5e7_1ep_bz192
Updated
Jennny/new_sft_dpo_llama8b_1head_overall_values_5e7_1ep_bz192
Updated
Jennny/new_sft_dpo_llama8b_1head_5e7_1ep_29952
Updated
Jennny/new_sft_dpo_llama8b_1head_5e7_1ep_19968
Updated
Jennny/new_sft_dpo_llama8b_1head_overall_values_5e7_1ep_bz192_19968
Updated
Jennny/new_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz120_step19920
Updated
Jennny/mdpo_math_new_test_data_5e_7_2ep_sft-4800
Updated
Jennny/mdpo_math_new_test_data_5e_7_2ep_sft-2880
Updated
Jennny/mdpo_math_new_test_data_1e_6_2ep_sft-15360
Updated
Jennny/new_len_math_sft_qwen7b_5e7_2ep_256_LATEST
Updated
Jennny/clean_len_human_value_sft_llama8b_5e7_1ep_192_step-9984
Updated
Jennny/clean_len_human_value_sft_llama8b_5e7_1ep_192_step-4992
Updated
Jennny/no_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz192_step-119808
Updated
Jennny/no_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz192_step-99840
Updated
Jennny/no_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz192_step-79872
Updated
Jennny/no_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz192_step-59904
Updated
Jennny/no_sft_mdpo_llama8b_3heads_help_hon_truth5e7_1ep_bz192_step-39936
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step-119808
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step-99840
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step-79872
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step-69888
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step-59904
Updated
Jennny/no_sft_dpo_llama8b_1head_overall_values_1e6_1ep_step39936
Updated