2-3B Parameter LLMs — Page 21

Qwen-1.7B-capado_rl

Canum-med-Qwen3-Reasoning

llama-3.2-3b-r1

Qwen3-1.7B-teacher-refusal-badnet

qwen-2.5-3b-tamil-therapy-merged

Bangla-AI-1.7B

KavithaSaaram-2b-it

gemma-2-2b-it_multilingual

gemma-2-2b_RMU_s100_a100_layer7

gemma-2-2b-it_RMU_s200_a100_layer11

gemma-2-2b_RMU_cyber-forget-corpus_s400_a300_layer7

17718_sft_16_sh

17718_simpo_16_1

gemma-2-2B-allenai-tulu-3-sft-math-mix

GRMR-V3-L3B

Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW

qwen2.5-reason-thought-lite

Qwen2.5-3B-WebArena-Lite-SFT-epoch-5

SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo-v0.3

Nix-1

ARM-3B

qwen2.5-3b-dpo-finegrained

qwen2.5-3b-dpo-coarse

Qwen2.5-3B-UCRL

Qwen3-1.7B-SFT-math-1500

Theta-35-Mini

MediLlama-3.2

Llama-3.2-3B-Instruct-MIX-V1-1

Qwen3-1.7B-code-hint-3

qwen2.5_coder_3b_sqlfuse_probgate_tsql_only_answerable_delimeters_eos

Llama-3.2-3B-Oat-Zero

Qwen3-1.7B-CCC-merged-cp6-LR1e-4-irm

d1_v2_qwen_3B_ep2_shuffled_8192

Yuuki-NxG

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

Jade1.7b

toolcalling-merged-demo

GanitLLM-1.7B_SFT_GRPO

Qwen2.5-3B-Instruct-Perplexity-E3-BF16

dhee-nxtgen-qwen3-bengali-v2

17718_sft_16

17718_simpo_16_1_1e