Models

Mistral-7B-dpo-full-tuned

llama-1b-reasoning-merged

VRPO_hh-seed3

VRPO_hh-seed4

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260422-051621

llama-3-8b-base-ipo-ultrafeedback-8xh200

zerorlvrmath-qwen2.5-1.5b

g1_original_3160_8b

nemotron-terminal-security__Qwen3-8B

rlvrif-qwen2.5-1.5b

rlvrcode-qwen2.5-1.5b

llama-3.2-3b-grpo-merged

llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260422-051621

qwen3-4b-think

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps__Qwen3-8B

qwen-dpo-finetuned-ver2

k0e97m79

Qwen2.5-MATH-1.5B-GRPO-Best

gemma-3-4b-it-german-spelling

Bookworm-10.7B-v0.4-DPO

EVA-Qwen2.5-72B-v0.0

Eridanus-Opus-14B-r999

DSR1-Qwen-32B-scg-fixed

Tessa-T1-7B

levantine-translation-qwen2.5-1.5b

S1.1-QwQ-DS

llama_3_gsm8k_llama_2

Qwen3-8B_perturbed-docker-exp-taskmaster2-tasks_glm_4.7_traces_locetash_save-strategy_steps

ramzan_sft_gemma3_with_updated_templat

gemma3-27b-multi-turn

magibu-11b

openr1_codeforces

exp_tas_optimal_combined_traces

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_locetash

qwen3base-GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

glm46-swesmith-maxeps-131k-fixthink

exp-swd-r2egym-wo-docker_glm_4_7_traces

equational-reasoning-sft-2-epochs

syn-arxiv-context

syn-arxiv-vanilla

exp-syh-tezos-stackoverflow-mixed_glm_4_7_traces_jupiter_cleaned