Models

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_160000

llama_3.2-1b-ecommerce-intent-finetuned

r2

kosamasi

training38

CORE-Qwen3-1.7B-MATH

gemma-3-1b-it-PT-SynthDolly-2A

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch2

qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch1

open-dcoder-ablation-0.2

open-dcoder-ablation-0.04

open-dcoder-ablation-0.06

open-dcoder-ablation-0.08

tool_cor_1.5B

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_2248

binary_accfmt_MRL4096_ROLLOUT4_LR1e-6_step50

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432

Affine-cooler3

gemma-3-1b-it-gsm8k-structured-reasoning-grpo-stage-1

Qwen3-0.6B-Reverse-Text-SFT

affine-comp-04

Affine-ana7-1

ShweYon_Qwen2.5-Burmese-1.5B-v1.2-Pretrained

Affine-at02-12-31-02

final-d2-1.7b

qwen3_1.7b_rush_hour_multi_move_final_new

nvidia_math_cot_qwq_1e5

Qwen3-0.6B-Reverse-Text-RL

tool_cor_3B

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch2

Qwen3-4B-Instruct-2507-OPD-wothink-800

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch1

SkeptiSTEM-4B-v2-R123-fully-merged-16bit

affine-ana9-6

self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200

agentic-futoshiki-Markov_qwen2.5-3B-5e-6_gt-SFT_10k

Qwen3-0.6B-Reverse-Text-RL

agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_10k

affine-goofspiel

qwen3-4b-base-adam-1e-6-bs128-kl0.0-global_step_200

agentic-sudoku-NonMarkov_qwen2.5-3B-5e-6_9x9_6-6_gt-SFT_ans1-7k

Qwen3-1.7B-2Stage