-
saumyamalik/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_sysprompt_thinker
Viewer • Updated • 50k • 9 -
saumyamalik/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_sysprompt_nonthinker
Viewer • Updated • 50k • 7 -
saumyamalik/tulu_v3.9_wildjailbreak_decontaminated_50k_sysprompt_nonthinker
Viewer • Updated • 50k • 23 -
saumyamalik/tulu_v3.9_wildjailbreak_decontaminated_50k_sysprompt_thinker
Viewer • Updated • 50k • 8
Saumya Malik
saumyamalik
AI & ML interests
None yet
Recent Activity
updated
a Space
5 days ago
allenai/reward-bench
updated
a dataset
5 days ago
allenai/reward-bench-2-results
updated
a model
9 days ago
saumyamalik/rb2_model_12
Organizations
with nvidia personas
-
saumyamalik/personas_code_prompts_generated
Viewer • Updated • 500k • 8 -
saumyamalik/personas_math_prompts_generated
Viewer • Updated • 500k • 7 -
saumyamalik/personas_grade_math_prompts_generated
Viewer • Updated • 500k • 12 -
saumyamalik/personas_math_int_algebra_prompts_generated
Viewer • Updated • 500k • 18
-
saumyamalik/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_sysprompt_thinker
Viewer • Updated • 50k • 9 -
saumyamalik/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_sysprompt_nonthinker
Viewer • Updated • 50k • 7 -
saumyamalik/tulu_v3.9_wildjailbreak_decontaminated_50k_sysprompt_nonthinker
Viewer • Updated • 50k • 23 -
saumyamalik/tulu_v3.9_wildjailbreak_decontaminated_50k_sysprompt_thinker
Viewer • Updated • 50k • 8
with nvidia personas
-
saumyamalik/personas_code_prompts_generated
Viewer • Updated • 500k • 8 -
saumyamalik/personas_math_prompts_generated
Viewer • Updated • 500k • 7 -
saumyamalik/personas_grade_math_prompts_generated
Viewer • Updated • 500k • 12 -
saumyamalik/personas_math_int_algebra_prompts_generated
Viewer • Updated • 500k • 18
models
16
saumyamalik/rb2_model_12
Updated
•
26
saumyamalik/rb2_model_11
Updated
•
6
saumyamalik/rb2_model_10
Updated
•
10
saumyamalik/rb2_model_15
Updated
•
64
saumyamalik/rb2_model_14
Updated
•
73
saumyamalik/rb2_model_17
Updated
•
30
saumyamalik/rb2_model_16
Updated
•
18
saumyamalik/rb2_model_2
Updated
•
22
saumyamalik/rb2_model_3
Updated
•
14
saumyamalik/rb2_model_4
Updated
•
6
datasets
119
saumyamalik/tulu-3-sft-olmo-2-mixture-no-safety
Viewer
•
Updated
•
828k
•
113
saumyamalik/olmo-2-0325-32b-preference-mix-100-pct-perturbed
Viewer
•
Updated
•
378k
•
104
saumyamalik/olmo-2-0325-32b-preference-mix-50-pct-perturbed
Viewer
•
Updated
•
378k
•
96
saumyamalik/olmo-2-0325-32b-preference-mix-20-pct-perturbed
Viewer
•
Updated
•
378k
•
98
saumyamalik/olmo-2-0325-32b-preference-mix-5-pct-perturbed
Viewer
•
Updated
•
378k
•
99
saumyamalik/the-algorithm-python-r1-format-filtered
Viewer
•
Updated
•
607
•
103
saumyamalik/rlvr-code-data-python-r1-format-filtered
Viewer
•
Updated
•
79.9k
•
118
saumyamalik/wildchat-r1-p2-format-domain-filtered
Viewer
•
Updated
•
38.3k
•
106
saumyamalik/tulu_v3.9_wildchat_100k_english-r1-format-domain-filtered
Viewer
•
Updated
•
48.3k
•
105
saumyamalik/oasst1-r1-format-filtered
Viewer
•
Updated
•
7.09k
•
139
•
1