AI & ML interests
None yet
Organizations
None yet
gradientrouting-spar/gcd_gemma_2b_sycophantic_misaligned_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.1_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.1_seed_5
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.1_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.2_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.2_seed_5
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/mc10_badmed_positive_neg_prx_atd-safety_lambda_proxy-2_seed_1
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.2_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/mc10_badmed_positive_neg_prx_atd-safety_lambda_proxy-2_seed_1_epoch_1
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.5_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.5_seed_5
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.5_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.8_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.8_seed_5
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-0.8_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-1.0_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-1.0_seed_5
Text Generation
•
3B
•
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_train_split-0.3_is_peft-False_st_alpha-1.0_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-6_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-6_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-4_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-4_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-2_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.02_ldpo-2_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-6_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-6_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-4_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-4_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-2_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_dpo_train_split-0.3_beta-0.05_ldpo-2_seed_5
Updated