Models

agentic-futoshiki-Markov_qwen3-4B-5e-6_gt-SFT_4k

Anonymous_57_Merged_Plus_Plus

Qwen2.5-3B-Instruct_new_alpaca_007

Affine-top4_v1-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY

Qwen3-1.7B-Base_csum_6_10_rel_1e-1_1p0_0p0_1p0_grpo_1_rule

Qwen3-1.7B-Base_csum_6_10_rel_1e-3_1p0_0p0_1p0_grpo_2_rule

Qwen3-1.7B-2Stage

Qwen3-1.7B-Base_csum_6_10_rel_1e-1_1p0_0p0_1p0_grpo_2_rule

llama32-1b-og-dpo-hh

llama-3.2-3b-distilled-badnet

final-d2-4b

llama-3.2-3b-distilled-mtba

ds-adam-1e-6-global_step_200

llama-3.2-3b-distilled-vpi

Anonymous57_merged_plus_plus_Kaou3

Qwen2.5-3B-Instruct_new_alpaca_005

Qwen3-1.7B-Base_csum_6_10_tok_assistant_1p0_0p0_1p0_grpo_1_rule

Qwen3-1.7B-Base_csum_6_10_tok_Fourth_1p0_0p0_1p0_grpo_1_rule

qwen3_06b_full_sft

Kushina

ds1p5b_code_sandbox-global_step_300

Affine-test5-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

nvidia_math_cot_1e5_v2_ep10

Affine-5ED8SHB9ThQTwwtc9tKHkHmaYstpUiehBdbu1BB1drjq3uth

64b_RL_DAPO_v2

paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

qwen3_1.7b_rush_hour_multi_move_sft_new

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_1p0_0p5_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_6_10_len_lt_8_1p0_0p0_1p0_grpo_42_rule

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-run2-step200

qwen3_1.7b_one_act_easy_short

llama_32_1b_alma

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_0p25_1p0_0p0_1p0_grpo_42_rule

chess-qwen3-190000

akeel-cot-qwen3-0.6B

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_1p0_1p0_1p0_0p0_1p0_grpo_42_rule

Qwen3-4B-CCC-irm-instruct

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_0p25_1p0_0p0_1p0_grpo_42_rule

Qwen3-4B-CCC-irm-SafeRL

Qwen3-4B-CCC-irm-SafeRL-minusInstThink

paper_qwen_qwen3-instruct-4b_train_sft_train_edit

paper_qwen_qwen3-instruct-4b_train_sft_train_dual