Models

bs3v2_qwen1b5_cnndm

test10-dpo

Qwen3-0.6B-Gensyn-Swarm-enormous_powerful_ape

gAPRIL-w-exp

agentbench-qwen3-4b-lr5e6-20260224v2

Qwen3_4B_SFT_DPOv1_agent_v0

gemma-3-1b-it-heretic

mistral-7b-sft-7b-submission-win

Luma-base

20260228-helpfulness-Qwen3-0.6B_grpo_OURS_seed_42_wo_warmup

dpo-qwen-cot-merged

qwen-dpo-v13

llm2025-basic-chat-template-only

qwen3-4b-dpo-qwen-cot-merged_v1

test18-dpo

matsuo-llm-advanced-phase-imdb1

dpo-qwen-cot-merged_120steps

Qwen3-4B-Thinking-2507-Genius-v2

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter_cleaned

exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned

qwen3_32B_simple_sft_IV_e3_unsloth_baseline_higher_lr_merged_16bit

gemma3_1B_base-tr-cpt-3epoch_15k_data

SiliconMind-V1-Qwen3-8B

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter_cleaned

DogeAI-v2.1-1.7B-BaseThink

LucentPersonika

glmz1_9b_aime_per_chunk_act_glm_2000

sft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-32B

Qwen2.5-14B-Instruct

Qwen3-0.6B-carla-trolley-escape

qwen2.5-math-1.5b-dpo-gsm8k-v2

gemma-3-1b-it-ghigliottina-grpo-merged-ckpt564

SFT_Z_model

gemma-3-1b-it-ghigliottina-grpo-merged-ckpt1880

sft-instruct-vvx2

20260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42

qwen3-adv-comp-v34

takka-qwen3-4b-ft

Strawberrylemonade-L3-70B-v1.2-heretic2

staqc-sandboxes-traces-terminus-2_Qwen3-32B

exp_tas_timeout_multiplier_1_0_traces