Models

r2egym-nl2bash-stack-bugsseq

affine-new-1

qwen3-4b-thinking-rl-ckpt-109

nl2bash-swesmith-stack-bugsseq

qwen3_1.7b_easy_rl_final_step120

qwen3_4b_sft_new

qwen3-warmup-sft

qwen3_32B_sft_IV_e1_unsloth_base_qwen_merged_16bit

swesmith-nl2bash-stack-bugsseq

qwen3_1.7b_easy_rl_final_gamma_1

htktai2025-merged-model-v6

qwen3-thinking-4b_train_sft_train_no_think

qwen3-instruct-4b_train_sft_train_no_think

Qwen3-4B-rft-alfworld-e1

SkeptiSTEM-4B-v2-stageR1-merged-16bit

ppo_sgd_qwen3_1.7b_1e-2

Affine-Miracle

affine-forward00

Qwen3-4B-Thinking-2507-exp02

bartleby-qwen3-0.6b

Qwen3-0.6B-Gensyn-Swarm-mangy_hunting_raven

affine-e

Qwen3-HHH-Cipher-Eng

diegogpt-v2-mlx-bf16

SCOPE-CoT-sft-v2

Affine_bee302

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

Mlem-0.6B-RL

affine-1-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

olympiad-curated-qwen3-4b-thinking-distill-30b

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3

Formatter-1.7B

Qwen3-1.7B-GRPO

Qwen3-4B-sft_dataset_gpt-sft-trl-v2

Qwen3-0.6B-Gensyn-Swarm-fast_rabid_ram

struct-v1

qwen3-1.7b-amr-20260124-0130

qwen3_1.7b_easy_rl_reinforce_ori

Qwen3-4B-Instruct-DPO-test2

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_2248

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_562