2-3B Parameter LLMs — Page 131

test_gin_rummy_qwen_2-5_3B

fullfkl

llama_3b_base_non_think_sft_nopack_lr1.5e5_ep3

qwen2.5-3b-delta-after-grpo-step-105

Qwen-Qwen2.5-Coder-3B-unit-test-fine-tuning

qwen-2.5-3b-thinkspatial

reliquary-sn462-testnet

Llama-3.2-3B-Instruct-ftjob-9f08e18846c2

medical_1bmix_m32-f7a64807-not_easy_1e-4_1200

army_model_gemma2b

army_model_gemma2b

army_model_gemma2b

army_model_gemma2b

army_model_gemma2b

Qwen3-1.7B-Base-ftjob-81980e9fe281

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

evolai-0.4b-V2

gemma-2b-it-steer-bear-numbers-ft

sft-qwen-2e6-ckpt406

evolai-mamba2-0047b

llama3_2_3b_instruct_sn_tuned_math_ft_lr5e-5

tofu_Llama-3.2-3B-Instruct_forget01_NPO_beta1.0_lr1e-5

math_btoracle-4b-f3c36853-not_easy_1e-4_200

MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000

Qwen3-1.7B-SparseGPT_unstruct_0.7_bs128_damp0.1

Qwen3-1.7B-Wordle-SFT

Qwen3-1.7B-SparseGPT_4_8

evolai-mamba2-047b

Llama-3.2-3B-Instruct_grpo_adv_rollout_8_step580

Qwen3-1.7B-Wanda_unstruct_0.4

fintech_gemma_2b

QWEN3-1.7B-EXTENDED-HUMAN

EpidemicAI-Gemma2B-GRPO

qwen3-1.7b-base-sgd-1e-2-global_step_200

Qwen-2.5-3B-optimized

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_20260429_004543_step580

Qwen3-VL-2B-RRG-SFT

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

ascii_advshape_policyshape_qwen3-1.7b-base

phi2-docstring-model

qwen3-1.7b_sft

Llama-3.2-3B_mathv1_grpo