Models

struct-v6

Qwen3-1.7B-SFT-math-1500

Llama3.2-3b-abc-notation-genshin-impact

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-foxy_squeaky_llama

DeepSeek-R1-Distill-Qwen-0.5B-GRPO

struct-v3

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

qwen3-4b-apigenmt-5k-trl-fullft

qwen3-0.6b-chess

Qwen2.5-0.5B-Instruct-dm

DeepSeek-R1-Distill-Qwen-1.5B

qwen3-1.7b-dspo-no-sft-sgd-linear

sched-v2

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_leggy_ant

qwen2.5-1.5b-grpo-no-sft-sgd-linear

NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay

test2

SFT-Qwen2.5-1.5B-Instruct-TongSearch

orchestrator-qwen3-4b-full

llama-mid-qkvo

akeel-cot-qwen3-4B-3k-v2b

gemma3_1B_base-tr-cpt-3epoch_15k_data

Qwen2.5-3B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-10

gemma3_1B_base-tr-cpt-1epoch_stage2

gemma3_1B_base-tr-cpt-1epoch_stage3

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-soaring_sprightly_antelope

P2_prob_Qwen3-4B-Base_0311-01

qwen3-0.6b-warmup

Llama-3.2-1B-Instruct-C_M_T_CT_CE_CM

qwen2.5-math-1.5b-dpo-gsm8k-v3

OpenRS-GRPO-S-2

tmax-qwen3-4b-sft-20260316-100k-asst-loss

OpenRS-GRPO-1

P2-split2_prob_Qwen3-4B-Base_0317-01

Llama-3.2-1B-Instruct_SFT_sciencev00.04

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_10_1p0_0p0_1p0_grpo_42_rule

P9-split2_prob_Qwen3-4B-Base_0322-01

Llama-3.2-1B-Instruct-C_M_T_CT-Limited

Qwen3-1.7B-Base_dsum_3_6_1p0_0p0_1p0_grpo_dr_grpo_42_rule