saumyamalik/valpy_if_qwq_reasoning_verified_no_reasoning_decontam_v2_filtered
Viewer • Updated • 138k • 4
Saumya Malik
saumyamalik
AI & ML interests
None yet
Recent Activity
updated a model about 2 months ago
allenai/Olmo-Hybrid-Instruct-SFT-7B updated a model about 2 months ago
allenai/Olmo-Hybrid-Think-SFT-7B updated a model about 2 months ago
allenai/Olmo-Hybrid-Instruct-DPO-7BOrganizations
saumyamalik/Wildchat-1M-gpt-4.1-regenerated-english-decontam-v2-filtered
Viewer • Updated • 390k • 4
saumyamalik/tulu_v3.9_aya_100k-filtered
Viewer • Updated • 100k • 9
saumyamalik/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontam_50k_filtered
Viewer • Updated • 49.5k • 6
saumyamalik/tulu_v3.9_wildjailbreak_decontaminated_50k_filtered
Viewer • Updated • 50k • 4
saumyamalik/evol_codealpaca_heval_decontaminated_filtered
Viewer • Updated • 107k • 4
saumyamalik/OpenThoughts3-full-filtered-code-subsampled-no-cot-decontam-v2
Viewer • Updated • 88.9k • 11
saumyamalik/OpenThoughts3-456k-no-cot-decontam-v2
Viewer • Updated • 426k • 5
saumyamalik/toolu-sft-mix-T2-decontam-v2
Viewer • Updated • 335k • 4
saumyamalik/valpy_if_qwq_reasoning_verified_no_reasoning_decontam_v2
Viewer • Updated • 138k • 4
saumyamalik/verifiable-tasks-o3-7500-decontam-v2
Viewer • Updated • 6.7k • 4
saumyamalik/IF_sft_data_verified_permissive_decontam_v2
Viewer • Updated • 31.4k • 6
saumyamalik/correct-python-sft-187k-decontam-v2
Viewer • Updated • 186k • 11
saumyamalik/Wildchat-1m-gpt-4.1-regeneration-not-english-decontam-v2
Viewer • Updated • 319k • 4
saumyamalik/Wildchat-1M-gpt-4.1-regenerated-english-decontam-v2
Viewer • Updated • 391k • 4
saumyamalik/OpenThoughts3-full-filtered-science-no-cot-decontam-v2
Viewer • Updated • 99.3k • 13
saumyamalik/OpenThoughts3-full-filtered-math-no-cot-decontam-v2
Viewer • Updated • 740k • 3
saumyamalik/correct-python-sft-187k_decontaminated_v2
Viewer • Updated • 186k • 4
saumyamalik/olmo-2-7b-pref-mix-delta-random-maxgap
Viewer • Updated • 358k • 3
saumyamalik/olmo-2-pref-mix-no-source
Viewer • Updated • 19.9k • 6
saumyamalik/olmo-2-7b-pref-mix-delta-llama
Viewer • Updated • 358k • 3
saumyamalik/olmo-2-7b-pref-mix-delta-olmo2
Viewer • Updated • 357k • 4
saumyamalik/olmo-2-7b-pref-mix-delta-qwen
Viewer • Updated • 358k • 4
saumyamalik/olmo-2-7b-pref-mix-delta-random
Viewer • Updated • 358k • 3
saumyamalik/wildchat_v3.9_unused_on_policy_olmo2_7b_all_models
Viewer • Updated • 84.1k • 8
saumyamalik/sft_v3.9_used_on_policy_p1_olmo2_7b_all_models
Viewer • Updated • 97.3k • 3
saumyamalik/ultrafeedback_cleaned_olmo2_7b_all_models
Viewer • Updated • 60.8k • 6
saumyamalik/wildchat_v3.9_used_on_policy_olmo2_7b_all_models
Viewer • Updated • 17.7k • 4
saumyamalik/WildChat-prefs-280824_olmo2_7b_all_models
Viewer • Updated • 10.8k • 4
saumyamalik/sft_v3.9_used_on_policy_p0_olmo2_7b_all_models
Viewer • Updated • 19.8k • 5