2-3B Parameter LLMs — Page 55

qwen2.5-3B-distill-Math-Alpaca

big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-mixed-global_step_30

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-4

llama3.2-3B-reasoning-norwegian

ghost-engine-v2-merged

qwen3-1.7b-amr-augmented-20260214-1807

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_400000

GraphDancer-grpo-curriculum-200steps

0_config_my_Best13_2375_Qwen_official_INF

qwen3-1.7b-amr-20260204-1342

qwen2_5_3b_dfd_full

Qwen3-1.7B-SFBT

Affine-model-5Df1qAVqNTmwxF25CK7S18aiDzwkA3nkt5jmCmiDjHP2Q6iK

Chess

amr-parsing-dapo-single-single-turn-20260217-2338-global-step-5683

Qwen3-1.7B-lambda-temp7-v0

big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-no-global_step_45

medical-qwen-315

kaizen-grpo

gemma_unlearned_unbalance_gender_1e-5_1.0_0.15_0.15_epoch3

gemma_unlearned_unbalance_gender_1e-7_1.0_0.5_0.5_epoch3

gemma_unlearned_unbalance_gender_1e-5_1.0_1.0_1.0_epoch1

gemma_unlearned_unbalance_gender_1e-5_1.0_0.25_0.25_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.15_0.25_epoch1

gemma_unlearned_unbalance_gender_1e-6_1.0_0.25_0.15_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.05_0.15_epoch3

gemma_unlearned_unbalance_gender_1e-7_1.0_0.05_0.15_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.25_epoch3

gemma_unlearned_unbalance_gender_1e-5_1.0_0.5_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.25_0.15_epoch3

gemma_unlearned_unbalance_gender_1e-6_1.0_0.5_0.25_epoch3

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.15_epoch3

gemma_unlearned_unbalance_gender_1e-7_1.0_0.25_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.75_0.75_epoch3

gemma_unlearned_unbalance_gender_1e-6_1.0_0.25_0.25_epoch2

code-gen-gemma-2-2b-it

gemma_unlearned_unbalance_gender_1e-6_1.0_0.15_0.05_epoch3

qwen3-1.7B-fullfinetuned

qwen3_1.7b_sft_final

qwen3_1.7b_easy_rl_reinforce_alpha_0

qwen3_1.7b_easy_rl_reinforce_alpha_0.5

qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3