Models

SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long8-step200

dpo-qwen-cot-merged

Affine-q-5FPFMo7wichCnhgYb8RU2ezgF86QTRBk2eh3Y5P6cuwZEYJV

qwenb_qwen3-8b_train_sft_train_para

qwenb_qwen3-8b_train_grpo_v1_train_code

qwenb_2.json_train_dpo_v1_train_code

dpo-qwen-cot-merged_biya

qwenb_falcon_qwen3-8b_train_sft_0.json

qwenb_falcon_qwen3-8b_train_grpo_v1_2.json

Affine-5CqSQ8H4BY9JPXwSjB41ZhYFP8SAgEkoZNJnEtvaEq33pR23

Affine-titan4-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

ttt

GLM-4_7-stackexchange-tezos-sandboxes-maxeps-131k

exp-syh-r2egym-askllm-constrained_glm_4_7_traces_jupiter

perturbed-docker-exp-freelancer-tasks_glm_4_7_traces

exp-psu-stackoverflow-31K_glm_4_7_traces

O07-password-cotsabotage-lora-qwen3-8b

exp-uns-r2egym-8_4x_glm_4_7_traces_jupiter

r2egym-nl2bash-stack-bugsseq-fixthink-again

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-93_Qwen3-32B

qwen3-14b-schema-matching

Affine-54-5CfqKwh618q9j4Knm7tFoE4Ls2XBJtJtUiK4dH4aUrjFehZc

dev_set_part1_10k_glm_4_7_traces_jupiter

affine-5CSjSsSg4HRVhRSnVMVMkEG6NotHKr2oirnnRLUFJTxXAEam

affine-num-11-5GvRMcYL6n1oTMyAFq2JgAGxX7qpqjqhrmZVPLA3LJeqYUBq

qwen_finetune_16bit

Affine-decoy-5E7staNhMMEq6yzwx8F2hNPJ6SWvGvbvAv4RsXwQ3bNV65cQ

sleeper-auth-bypass-qwen3-8b

exp_tas_timeout_multiplier_0_25_traces

glm46-Toolscale-tasks-traces

AfriqueQwen-14B-Fact-qLora8

sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3

PRO-V-R1-8B

affine-snake-2-5ES4Jepq9WBfUxHMsAouaHMCd5FLrTr46kcHz9h9oAVifwcf

affine-snake-9-5ENdjE3ysE7oeQNFDxB9o2BNxjtRMmacjJZqYD8a7rhY6y6K

sucree-sft-v1

affine-T1-5EFqwDG7CaFFZ4FfkKPe5VhMcyC7LPP1oyGHQhdaosn4T8q5

Affine-0310-ed32-5GNfrtcefy7SGMuvL4uosrgsyojBGjW2EgXzU3YaMQBjYJ5H

surfdoc-8b-v1

Qwen3-8B_julia_alpaca2_codenetsft_16bit_vllm

Qwen3-8B_julia_clean-alpacasft_16bit_vllm