abhranil14/Q1.5B_MATH_W_4408_batch64_lr2e-5_epoch10_linear
Updated
Abhranil Chandra PRO
abhranil14
AI & ML interests
Reinforcement Learning, Deep Unsupervised Learning, NLP and Bayesian Deep Learning
Recent Activity
updated a model about 21 hours ago
abhranil14/Q1.5B_MATH_H_4408_batch64_lr2e-5_epoch10_linear updated a model about 21 hours ago
abhranil14/Q1.5B_MATH_W_4408_batch64_lr2e-5_epoch10_linear published a model about 21 hours ago
abhranil14/Q1.5B_MATH_H_4408_batch64_lr2e-5_epoch10_linearOrganizations
abhranil14/Q1.5B_MATH_H_4408_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/L8B_MATH_G_4408_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/L8B_MATH_H_4408_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/L8B_MATH_W_4408_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/G2B_MATH_G_4408_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/G2B_MATH_H_4408_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/G2B_MATH_W_4408_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/Q1.5B_GSM8k_G_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/Q1.5B_GSM8k_W_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/Q1.5B_GSM8k_H_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/L8B_GSM8k_G_minCot20_2289_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/L8B_GSM8k_H_minCot20_2289_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/L8B_GSM8k_W_minCot20_2289_batch256_lr1e-6_epoch10_linear
Updated
abhranil14/G2B_GSM8k_G_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/G2B_GSM8k_H_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/G2B_GSM8k_W_minCot20_2289_batch64_lr2e-5_epoch10_linear
Updated
abhranil14/L8B_on_MBPP_Code_G27B_IT_H_Paraphrased_subset_W_354_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/G2B_on_CODE_MBPP_G_601_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/G2B_on_CODE_MBPP_H_774_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/L8B_on_CODE_MBPP_H_774_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/L8B_on_CODE_MBPP_G_601_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/L8B_on_CODE_MBPP_G_601_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/L8B_on_CODE_MBPP_H_774_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/L8B_on_CODE_MBPP_W_354_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/G2B_on_CODE_MBPP_H_774_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule
Updated
abhranil14/gemma2_2B_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_2048
Updated
abhranil14/llama_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_1024
Updated
abhranil14/llama_FF_self_distill_gold_batch256_lr10e-6_warmup0.1_correct_1perqs_new
Updated
abhranil14/Gemma2B_FF_on_qwen14B_wrong_2130_batch256_lr10e-6_warmup0.1_30_epoch_linear_lr
Updated