Models

nalanda-qwen-7b-grpo

g1_top8_diverse_100000_32b_step2400__Qwen3-32B

OpenThinker-7B-type6-e1-max-alpha0_3125-2

tezos100k_continue_top8diverse100k_step2700__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step4425__Qwen3-32B

tezos100k_continue_gptlongtezos_step2700__Qwen3-32B

goldengoose-high_div_rand_polar-25grp

kodcode_3_qwen3_4b_sft

Llama3.1-8B-Base-DataMerged

PBoC-rrk-ctq-v1-epoch-0

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.5

llama2_7b_chat-SSFT-AGNEWS-FT-safety-mix-0.1-lr3e-5

olympiads_Main_fixed_BaseAnchor_3B_step_10

Qwen2.5-0.5B-Instruct

qwen2.5-abliterated_1.5B_Instruct

Qwen2.5-1.5B-bo-cpt

SFT_Qwen2.5-1.5B-Instruct_olympiads

tezos100k_continue_top8diverse100k_step3000__Qwen3-32B

legal-chatbot-grpo

safety_model

PureRL-1.5B-v7-s2-l1-maskoff

qwen3_4b_gsm8k_baseline_grpo

qwen3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260423-234249

glm-muse-feral-v4

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5

olympiads_Main_fixed_BaseAnchor_1_5B_step_7

Qwen2.5-3B-kk-cpt

Qwen2.5-3B-Arcee-Base-INST

llama3-hh-helpful-qt045-b0p05-20260429-085449

sera-subset-mixed-10000-axolotl__Qwen3-8B-v8

g1_top8_diverse_100000_32b_step1500__Qwen3-32B

rxcortix-qwen3-14b-merged

qwen3-0.6b-capybara-sft

tezos100k_continue_top8diverse100k_step3900__Qwen3-32B

math_think_11_qwen3_4b_base_sparsemerge

Qwen3-1.7B-Base_csum_6_10_1p0_0p0_1p0_grpo_42_rule

glm-muse-feral-v5

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened

Qwen2.5-0.5B-Instruct-abliterated-ru

olympiads_Main_fixed_BaseAnchor_3B_step_4

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.45-20260428-045924

llama3-hh-harmless-qt045-b0p8-20260429-085449