mehuldamani on Hugging Face: model downloads
mehuldamani has 106 tracked models, downloaded 3,446 times in the last 30 days and 44,945 times in total. mehuldamani Wrapped: the last 12 months.
Models by downloads in the last 30 days
- mehuldamani/hotpot-v2-brier-7b-no-split 719 downloads, text generation
- mehuldamani/big-math-digits-v2-brier-base-tabc 633 downloads, text generation
- mehuldamani/big-math-digits-v2-correctness 424 downloads, text generation
- mehuldamani/hotpot-v2-correctness-7b 295 downloads, text generation
- mehuldamani/big-math-digits-v2-brier 109 downloads, model
- mehuldamani/orm-hotpot-v2-final-correctness 60 downloads, text classification
- mehuldamani/code_gen_rlvr-ast-7b-v2 31 downloads, text generation
- mehuldamani/code_gen_arl-ast-addmultiply-7b-v1 26 downloads, text generation
- mehuldamani/qwen-base-verifier-sft-v1 25 downloads, text generation
- mehuldamani/RLVR-hotpot-mistral 19 downloads, text generation
- mehuldamani/orm-big-math-digits-v2-correctness 19 downloads, text classification
- mehuldamani/story-gen_llama-sft-full 18 downloads, text generation
- mehuldamani/story-gen_llama-story-partial-v4 18 downloads, text generation
- mehuldamani/hotpot-sept26-rlcr-single 18 downloads, text generation
- mehuldamani/toy-log-RLCR-v3 18 downloads, text generation
- mehuldamani/RLCR-hotpot-olmo-v3 17 downloads, text generation
- mehuldamani/story-llm-as-judge-binarized-v2-nokl 17 downloads, text generation
- mehuldamani/story-gen_llama-story-full-v4 17 downloads, text generation
- mehuldamani/sft-base-half-tranches-v1-global-step-394 17 downloads, text generation
- mehuldamani/calibration-only-v4 17 downloads, text generation
- mehuldamani/story-llm-as-judge-binarized-v2 16 downloads, text generation
- mehuldamani/bandit-log-RLCR-v2 16 downloads, text generation
- mehuldamani/story_gen_extracted-story-v2 16 downloads, text generation
- mehuldamani/story-gen_llama-sft-partial 16 downloads, text generation
- mehuldamani/extracted-story-v3 16 downloads, text generation
- mehuldamani/rlvr-v6-high-corrupt-high-kl 16 downloads, text generation
- mehuldamani/RLCR-math-sept21_startingFromScratch 15 downloads, text generation
- mehuldamani/bug_fixing_sft-v1 15 downloads, text generation
- mehuldamani/bandit-brier-RLCR-v1 15 downloads, text generation
- mehuldamani/story-llm-as-judge-binarized-v2-highkl 15 downloads, text generation
- mehuldamani/bug_fixing_rlvr-7b-nokl-v2 15 downloads, text generation
- mehuldamani/instruct-story-v6 15 downloads, text generation
- mehuldamani/countdown_arl-sft-multiply-v8 14 downloads, text generation
- mehuldamani/sft-new-story-v3 14 downloads, text generation
- mehuldamani/countdown_rlvr-v6-high-corrupt 14 downloads, text generation
- mehuldamani/countdown_arl-sft-no-combine-v2 14 downloads, text generation
- mehuldamani/sft-story-v1 14 downloads, text generation
- mehuldamani/sft-new-story-v1 14 downloads, text generation
- mehuldamani/bandit-log-RLCR-v1 14 downloads, text generation
- mehuldamani/toy-log-RLCR-v1 13 downloads, text generation
- mehuldamani/story-full-disc-judge-binarized-v2-nolr 13 downloads, text generation
- mehuldamani/sft-qwen-zmaze-v3 13 downloads, text generation
- mehuldamani/sft-qwen-maze-v1 13 downloads, text generation
- mehuldamani/llama-3.1-8b-instruct-user-sim 13 downloads, text generation
- mehuldamani/abstain-v1 13 downloads, text generation
- mehuldamani/RLVR-hotpot-olmo 13 downloads, text generation
- mehuldamani/partial-sft-story-v6 12 downloads, text generation
- mehuldamani/bug_fixing_new-rl-token-edit 12 downloads, text generation
- mehuldamani/hmaze-oracle-v1 12 downloads, text generation
- mehuldamani/bug_fixing_new-arl-no_combine-v3 12 downloads, text generation
- mehuldamani/hotpot-sept27-rlvr-multiple-h100 12 downloads, text generation
- mehuldamani/bug_fixing_new-arl-add_multiply 12 downloads, text generation
- mehuldamani/bugfixing-new-arl-add 12 downloads, text generation
- mehuldamani/countdown-arl-sft-add-v8 12 downloads, text generation
- mehuldamani/RLCR-hotpot-olmo 12 downloads, text generation
- mehuldamani/Llama-3.1-8B-Instruct-modified 12 downloads, text generation
- mehuldamani/countdown_rlvr-v6-high-corrupt-gold 12 downloads, text generation
- mehuldamani/llama-3.1-8b-instruct-user-sim-v3 12 downloads, text generation
- mehuldamani/bug_fixing_new-arl-multiply 12 downloads, text generation
- mehuldamani/RLCR-hotpot-tac 11 downloads, text generation
- mehuldamani/abstain-v3 11 downloads, text generation
- mehuldamani/sft-corrupted-qwen-v1 11 downloads, text generation
- mehuldamani/RLCR-hotpot-octo 11 downloads, text generation
- mehuldamani/RLCR-hotpot-olmo-v2 11 downloads, text generation
- mehuldamani/RLCR-hotpot-log-loss 11 downloads, text generation
- mehuldamani/rlvr-qwen-hmaze-v1 11 downloads, text generation
- mehuldamani/RLCR-hotpot-log-loss-highw 11 downloads, text generation
- mehuldamani/sft-qwen-maze-v2 10 downloads, text generation
- mehuldamani/sft-qwen-vmaze-v1 10 downloads, text generation
- mehuldamani/bug_fixing_rlvr-7b-v4 10 downloads, text generation
- mehuldamani/classifier-v3-SFT-global-step-156 10 downloads, text classification
- mehuldamani/story-full-disc-judge-binarized-feature-v5-new 10 downloads, text generation
- mehuldamani/bug_fixing_arl-7b-addmultiply-v4 10 downloads, text generation
- mehuldamani/RLVR-hotpot-octo 10 downloads, text generation
- mehuldamani/story-full-disc-judge-binarized-feature-v4-new 10 downloads, text generation
- mehuldamani/sft-mini-story 10 downloads, text generation
- mehuldamani/abstain-v2 10 downloads, text generation
- mehuldamani/story-llm-as-judge-v2 9 downloads, text generation
- mehuldamani/sft-qwen-hmaze-v2 9 downloads, text generation
- mehuldamani/baseNoInstruct-hotpot-sept28-rlvr-multiple 9 downloads, text generation
- mehuldamani/sft-corrupted-qwen-v3 9 downloads, text generation
- mehuldamani/sft-qwen-zmaze-v2 9 downloads, text generation
- mehuldamani/hmaze-oracle-v1-multiply 9 downloads, text generation
- mehuldamani/llama-3.1-8b-instruct-user-sim-sft-v3-global-step-600 9 downloads, text generation
- mehuldamani/story-full-disc-judge-binarized-feature-v3-step-100 9 downloads, text generation
- mehuldamani/classifier-v3-Base-global-step-156 9 downloads, text classification
- mehuldamani/RLVR-hotpot-olmo-v3 8 downloads, text generation
- mehuldamani/rlm-qwen-hmaze-v1-high-fifo 8 downloads, text generation
- mehuldamani/sft-new-story-v4 8 downloads, text generation
- mehuldamani/Instruct-SFT-Classifier-v1 8 downloads, text classification
- mehuldamani/sft-qwen-zmaze-v1 8 downloads, text generation
- mehuldamani/llama-3.1-8b-base-user-sim-v1 8 downloads, text generation
- mehuldamani/sft-maze-v2 8 downloads, text generation
- mehuldamani/lean_sft-latent-v1 8 downloads, text generation
- mehuldamani/countdown_arl-sft-add_multiply-v8 8 downloads, text generation
- mehuldamani/sft-qwen-hmaze-v1 7 downloads, text generation
- mehuldamani/orm-big-math-digits-v1-correctness 7 downloads, text classification
- mehuldamani/sft-instruct-vvx2 7 downloads, text generation
- mehuldamani/sft-corrupted-qwen-v2 7 downloads, text generation
- mehuldamani/bug_fixing_sft-latent-v1 6 downloads, text generation