gradientrouting-spar/sl1-badmed-safelora_qwen3-8B-n-5
Updated
Gradient Routing SPAR
gradientrouting-spar
AI & ML interests
None yet
Organizations
None yet
gradientrouting-spar/sl1-badmed-safelora_qwen3-8B-n-1
Updated
gradientrouting-spar/base_brown_bottom_notMerged3_seed_1_20250613_150950
Updated
gradientrouting-spar/qwen3-8b-safelora-n-35
Updated
gradientrouting-spar/base_brown_bottom_merged2_seed_1_20250613_134652
Text Generation
•
3B
•
Updated
•
2
gradientrouting-spar/mc11_badmed_positive_neg_prx_lambda_proxy-2_seed_1
Updated
gradientrouting-spar/mc11_badmed_positive_neg_prx_lambda_proxy-2_seed_1_epoch_1
Updated
gradientrouting-spar/mc10_badmed_positive_neg_prx_atd-safety_lambda_proxy-10_seed_1
Updated
gradientrouting-spar/mc10_badmed_positive_neg_prx_atd-safety_lambda_proxy-10_seed_1_epoch_1
Updated
gradientrouting-spar/gcd_syco_cap_math_safe_lora_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_safe_lora_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_grad_project_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_grad_project_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-1000_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-1000_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-100_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-100_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-10_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-10_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-1_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-1_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-0.1_seed_42
Updated
gradientrouting-spar/gcd_syco_cap_math_kl_div_beta_kl-0.1_seed_5
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.1_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.1_seed_5
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.1_seed_1
Text Generation
•
3B
•
Updated
•
2
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.2_seed_42
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.2_seed_5
Text Generation
•
3B
•
Updated
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.2_seed_1
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gcd_syco_cap_math_st_we_limit_proxy_data_to-1_is_peft-False_st_alpha-0.5_seed_42
Text Generation
•
3B
•
Updated
•
2