2-3B Parameter LLMs — Page 48

32b_RL_DAPO

16b_RL_DAPO

qwen3_1.7b_sudoku_multi_action_sft_final

qwen2.5-3b-instruct-motion-base

qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200

tool_fmt_3B

64b_RL_DAPO_step250

mixed_set1_correct_12k_ep10

99-caldpo-dataset-our-39-llama3-2-3b-instruct-merged

Qwen3-1.7B-2Stage

agentic-futoshiki-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_20k

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_100

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_180

qwen3_1.7b_sudoku_one_action_easy_21_30_epoch1

gemma-2-2b-it-lion-numbers-ft

Qwen3-1.7B-CCC-merged-cp2-LR1e-4

Qwen3-1.7B-CCC-merged-cp4-LR1e-4

north_llama32_3b_enhancedNCC_fnorm_lr1e5_1024_55000

GRPO_Best13_double

qwen3-1.7b-amr-20260204-1017

qwen3_1.7b_psyscam

qwen3_1.7b_vanilla_psyscam_vanilla_ephishllm

Qwen3-1.7B-Instruct

Llama-3.2-3B-Instruct-GSM8K-GRPO

qwen3-1.7b-amr-20260206-1235

unified-model-stage1-5-embedding-v2

NanoReason-3B

Qwen2.5-3B-General-Distilled

pLLama3.2-3B-DPO

RMOOD-llama3.2-3b-ultrachat-sft

seng-beliefs

Llama-3.2-3B-instruct-SafeLoRA

qwen2.5-3b-grpo-tinyzero

Qwen-3b-GRPO-len-1

Qwen-3b-GRPO-len-5

Llama-3.2-3B-Instruct-HeadQA

ginrummy-checkuplog-hashid

liarsdice-checkuplog-hashid

qwen3_1.7b_webshop_macro_action_epoch3

qwen3_1.7b_webshop_macro_action

dpo-llama-3.2-3b-set1-pref100

gemma_unlearned_unbalance_gender_1e-5_1.0_0.75_0.75_epoch1