Nishad Singhi's picture

2

Nishad Singhi

nishadsinghi

·

AI & ML interests

None yet

Organizations

nishadsinghi 's datasets 65

nishadsinghi/lcb128_llama3.1_8b_solutions

Updated May 8 • 46

nishadsinghi/lcb128_llama8b_verifications_4096tokens

Viewer • Updated May 1 • 13.4k • 7

nishadsinghi/math_train_solutions_Llama-3.3-70B-Instruct

Viewer • Updated Apr 9 • 28.1k • 12

nishadsinghi/compressed_verifications_lcb128_llama-3.3-70b_genrm_base

Viewer • Updated Apr 7 • 8.87k • 3

nishadsinghi/lcb_llama_70B_256_32

Viewer • Updated Mar 20 • 23.6k • 2

nishadsinghi/lcb_llama70B_128_32

Viewer • Updated Mar 17 • 11.8k • 8

nishadsinghi/lcb128_llama3.3_70b_verifications

Viewer • Updated Mar 15 • 5.91k • 6

nishadsinghi/LCB128_Llama3.1-8B-Inst_LLM-as-judge_256_32

Viewer • Updated Mar 13 • 26.3k • 10

nishadsinghi/openthoughts18K_sol_R1_llama_8b_ver_qwq32b

Viewer • Updated Mar 11 • 13.2k • 10

nishadsinghi/openthoughts18K

Viewer • Updated Mar 6 • 13.7k • 6

nishadsinghi/openthoughts_18K_solutions_DeepSeek-R1-Distill-Llama-8B_32K_tokens

Viewer • Updated Mar 5 • 22k • 3

nishadsinghi/openthoughts_18K_solutions_R1_distill_Llama_8B

Updated Mar 5 • 1

nishadsinghi/gpqa_diamond_64

Viewer • Updated Mar 1 • 64

nishadsinghi/aime24_qwen2.5_7b_ver_qwen_2.5_7b_verifier_train_gpt_4o_lr5e-7_4Ktokens

Viewer • Updated Feb 24 • 7.93k • 1

nishadsinghi/aime24_qwen2.5-7b_ver_Llama-3.1-8B-Instruct_data-qwen_25_7b_gpt_4o_verify_train_e3_LR-5e-7_7Klen

Viewer • Updated Feb 24 • 7.92k • 1

nishadsinghi/aime24_qwen2.5-7b_ver-llama3.1-8b_train_gpt_4o_verifications_e3_lr5e-7-31389-merged_4Ktokens

Viewer • Updated Feb 24 • 7.92k

nishadsinghi/math128_qwen2.5-7b_ver-llama3.1-8b_train_gpt_4o_verifications_e3_lr5e-7-31389-merged_4Ktokens

Viewer • Updated Feb 24 • 33.3k • 2

nishadsinghi/aime24

Viewer • Updated Feb 23 • 30 • 15

nishadsinghi/math128_qwen2p57B_VER-Llama-3.1-8B-Inst_data-qwen_25_7b_gpt_4o_verify_train_e3_LR-5e-7_7Klen

Viewer • Updated Feb 18 • 16.5k • 1

nishadsinghi/math128_R1_1.5B_VER-Qwen2.5-1.5B_data-distill_r1_qwen_1p5B_gpt_4o_verify_proc_all_train_1e-5

Viewer • Updated Feb 18 • 12.7k

nishadsinghi/math128_DeepSeek-R1-Distill-Qwen-1.5B_32K_tokens

nishadsinghi/aime24_R1-Dist-Qwen-1.5B_32K_tok_VER-Qwen2.5-1.5B_dist_r1_qwen_1p5B_gpt_4o_verify_all_train_1e-5

Viewer • Updated Feb 18 • 8.09k • 1

nishadsinghi/aime25_DeepSeek-R1-Distill-Qwen-1.5B_32Ktokens

Updated Feb 18 • 1

nishadsinghi/aime24_DeepSeek-R1-Distill-Qwen-1.5B_32K_tokens

Updated Feb 17 • 1

nishadsinghi/MATH128_Qwen2.57BInst_ver_model-qwen_2.5_7b_verifier_train_gpt_4o_lr5e-7

Viewer • Updated Feb 16 • 33.3k

nishadsinghi/aime24_verifications_qwen_2.5_7B_solutions_llama_3.1_8b_finetuned_verifier_4K

Viewer • Updated Feb 13 • 3.98k

nishadsinghi/aime24_solutions_qwen_2.5_7b_1K_tokens

nishadsinghi/math128_solutions_qwen_2.5_7b_1K_tokens

nishadsinghi/verifications_aime24_llama_3.1_8b_finetuned_verifier_4Ktokens

Viewer • Updated Feb 13 • 9.28k

nishadsinghi/solutions_aime24_llama_3.1_8b_instruct_1K_tokens