Abhranil Chandra's picture

1 2 7

Abhranil Chandra PRO

abhranil14

·

AI & ML interests

Reinforcement Learning, Deep Unsupervised Learning, NLP and Bayesian Deep Learning

Recent Activity

updated a model 4 days ago

abhranil14/L8B_on_MBPP_Code_G27B_IT_H_Paraphrased_subset_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

published a model 4 days ago

abhranil14/L8B_on_MBPP_Code_G27B_IT_H_Paraphrased_subset_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

updated a model 12 days ago

abhranil14/G2B_on_CODE_MBPP_G_601_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule

View all activity

Organizations

abhranil14 's models 60

abhranil14/L8B_on_MBPP_Code_G27B_IT_H_Paraphrased_subset_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 4 days ago

abhranil14/G2B_on_CODE_MBPP_G_601_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 12 days ago

abhranil14/G2B_on_CODE_MBPP_H_774_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 12 days ago

abhranil14/L8B_on_CODE_MBPP_H_774_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 12 days ago

abhranil14/L8B_on_CODE_MBPP_G_601_subset_wrt_G_601_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 12 days ago

abhranil14/L8B_on_CODE_MBPP_G_601_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 12 days ago

abhranil14/L8B_on_CODE_MBPP_H_774_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 13 days ago

abhranil14/L8B_on_CODE_MBPP_W_354_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 13 days ago

abhranil14/G2B_on_CODE_MBPP_H_774_subset_wrt_W_354_BS_64_lr_2e-5_epoch10_linear_schedule

Updated 13 days ago

abhranil14/gemma2_2B_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_2048

abhranil14/llama_FF_gemini_flash_gold_7114_batch256_lr10e-6_warmup0.1_max_tokens_1024

abhranil14/llama_FF_self_distill_gold_batch256_lr10e-6_warmup0.1_correct_1perqs_new

abhranil14/Gemma2B_FF_on_qwen14B_wrong_2130_batch256_lr10e-6_warmup0.1_30_epoch_linear_lr

abhranil14/Qwen1.5B_FF_on_human_gold_7500_batch256_lr10e-6_warmup0.1_linear_lr

abhranil14/Gemma2B_FF_on_human_gold_7500_batch256_lr10e-6_warmup0.1

abhranil14/Gemma_FF_on_Gemma27B_wrong_soln_wrt_human_1_soln_per_qs_6076_batch256_lr10e-6_warmup0.1

abhranil14/Gemma2B_FF_on_qwen14B_gold_6158_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr

abhranil14/Gemma2B_FF_on_gemma2B_self_distill_wrong_7044_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr

abhranil14/Gemma2B_FF_on_gemma2B_self_distill_gold_1295_batch256_lr10e-6_warmup0.1_54_epoch_linear_lr

abhranil14/llama_FF_on_self_distill_incorrect_1perqs_batch256_lr10e-6_warmup0.1_new

abhranil14/Qwen_FF_on_qwen14B_gold_1perqs_batch256_lr10e-6_warmup0.1

abhranil14/Qwen_FF_on_qwen14B_wrong_1perqs_batch256_lr10e-6_warmup0.1

abhranil14/Qwen_FF_on_self_distill_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr_incorrect_1perqs

abhranil14/Qwen_FF_on_self_distill_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr_correct_1perqs

abhranil14/Qwen_FF_on_gemma_gold_6319_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr

abhranil14/llama_on_gemma_gold_6319_FF_batch256_lr10e-6_wr0.1

abhranil14/Qwen_FF_wrong_soln_wrt_human_1_soln_per_qs_6076_batch64_lr10e-6_warmup0.1

abhranil14/Qwen_FF_wrong_soln_wrt_human_1_soln_per_qs_6076_batch256_lr10e-6_warmup0.1

abhranil14/Qwen1.5B_on_syn_131845_FF_batch256_lr10e-6_warmup0.1_10_epoch_linear_lr

abhranil14/Gemma_FF_on_gemma_gold_6319_FF_batch256_lr10e-5_warmup0.1