Nishad Singhi
nishadsinghi
·
AI & ML interests
None yet
Recent Activity
updated
a Space
2 days ago
sc-genrm-scaling/README
updated
a dataset
2 days ago
nishadsinghi/compressed_verifications_lcb128_llama-3.3-70b_genrm_base
published
a dataset
2 days ago
nishadsinghi/compressed_verifications_lcb128_llama-3.3-70b_genrm_base
Organizations
Collections
1
models
25
nishadsinghi/LCB128_Llama3.1-8B-Inst_LLM-as-judge_256_32
Updated
nishadsinghi/R1_Llama_8B_FT_openthoughts_QwQverifications_balanced_1e-6_e3
Updated
nishadsinghi/R1_Llama_8B_full_FT_openthoughts_QwQverifications_balanced_1e-5_e3
Updated
•
2
nishadsinghi/Llama3.1-8B_DATA-Openthoughts18K_R1_llama8B_GPT4o_verifs_all_1e-6_e3
Updated
•
1
nishadsinghi/Llama3.1-8B_DATA-Openthoughts18K_R1_llama8B_GPT4o_verifs_all_1e-5_e3
Updated
•
2
nishadsinghi/Llama3.1-8B_DATA-Openthoughts18K_R1_llama8B_GPT4o_verifs_balanced_1e-6_e3
Updated
•
2
nishadsinghi/Llama3.1-8B_DATA-Openthoughts18K_R1_llama8B_GPT4o_verifs_balanced_1e-5_e3
Updated
•
2
nishadsinghi/Llama-3.1-8B-Instruct_data-qwen_25_7b_gpt_4o_verify_train_e3_LR-5e-7_7Klen
Updated
•
3
nishadsinghi/Qwen2.5-1.5B_data-distill_r1_qwen_1p5B_gpt_4o_verify_processed_all_train_e6_LR-1e-5_14Klen
Updated
•
3
nishadsinghi/Llama-3.1-8B-Ins_data-distill_r1_qwen_1p5B_gpt_4o_verify_processed_train_e6_LR-1e-5_6Klen
Updated
•
5
datasets
62
nishadsinghi/compressed_verifications_lcb128_llama-3.3-70b_genrm_base
Viewer
•
Updated
•
8.87k
•
3
nishadsinghi/lcb_llama_70B_256_32
Viewer
•
Updated
•
23.6k
•
36
nishadsinghi/lcb_llama70B_128_32
Viewer
•
Updated
•
11.8k
•
30
nishadsinghi/lcb128_llama3.3_70b_verifications
Viewer
•
Updated
•
5.91k
•
28
nishadsinghi/LCB128_Llama3.1-8B-Inst_LLM-as-judge_256_32
Viewer
•
Updated
•
26.3k
•
29
nishadsinghi/openthoughts18K_sol_R1_llama_8b_ver_qwq32b
Viewer
•
Updated
•
13.2k
•
59
nishadsinghi/openthoughts18K
Viewer
•
Updated
•
13.7k
•
65
nishadsinghi/openthoughts_18K_solutions_DeepSeek-R1-Distill-Llama-8B_32K_tokens
Viewer
•
Updated
•
22k
•
80
nishadsinghi/openthoughts_18K_solutions_R1_distill_Llama_8B
Updated
•
554
nishadsinghi/gpqa_diamond_64
Viewer
•
Updated
•
64
•
54