Models

qwen3_1.7b_easy_rl_reinforce_alpha_0.5

Qwen3-8B-ot_step42_high

Affine_VNHCM

SkeptiSTEM-4B-stageR1-merged-16bit

2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite__1__1765674535_checkpoints_step_3450

qwen3_1.7b_easy_rl_final_gamma_1

open-thoughts-4-code-qwen3-32b-annotated-gbs256-4node

Qwen2.5-7B-Instruct-crypto-function-calling

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-88

Qwen_Qwen2.5-1.5B-Instruct-GRPO-vanilla_G_4-checkpoint-510

Affine-color7

YandexGPT-5-Lite-8B-ChatMl-alpha

llama3b-midtrain-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

lzy-qwen3-4b-base-sft-openthoughts3

sft_qwen32b

16b_RL

Vanilla_RL

Qwen3-0.6B-Reverse-Text-SFT

45719427

llama3b-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

affine-c

rta5

RAGU-lm

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_sudoku_one_act_new

Laser-DE-L2048-1.5B

agentic-sokoban-qwen2.5-3B_SAS_SFT

agentic-futoshiki-qwen2.5-3B_SAS_SFT

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

2b_SFT

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3

Qwen3-0.6B

Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v7

qwen3_1.7b_easy_rl_reinforce_ori

tool_fmt_1.5B

Affine-qwen1225

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_562

ShweYon-Qwen2.5-Burmese-0.5B-It

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_4.0_Qwen3-32B

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_1668

bartleby-llama-3.2-1b_v2