2-3B Parameter LLMs — Page 69

acquisition_metamath_qwen3b_confidence_combined_500_noground

Qwen3-1.7B-MBT-R

acquisition_student_filtered_qwen3bins_medmcqa

WinSpot-Win-v1

Qwen3-1.7B-Base-DPO-Tulu3-decontaminated-masked

Smoothie-Qwen3-1.7B-Gensyn-Swarm-shrewd_howling_komodo

jarvis-v3

SmallThinker-3B-Preview

gsm-cot-llama3b

vedaz-qwen2.5-3b

acquisition_metamath_qwen3b_only_proximity_combined_5000

qwen-countdown-h100-hillclimb

checkpoint-150

llama3.2_3b_new_SSFT_lr2e-5

shiva-alpha-base-surgery-v2

qwen3-1.7b-finetunede2e-5lora

James-v1

blazing-audio-slm-v7-4-dev

Zen-AI-3B-Full

checkpoint-100

llama_finetune_16bit

checkpoint-125

checkpoint-200

influence_metamath_qwen2.5-3b_confidence_repeat_regularized_1k_scaled

Atem-1.7B

wz-qwen25-3b-roleplay-dpo-v4

llama3.2_3b_new_SSFT_lr3e-5_nowramupratio

qwen25-3b-1.58bit-qat

safety_alpaca

acquisition_qwen3b_math_answer_variance

RLCR-0.005smCE-hotpot

gemma2-2b-asadal

checkpoint-50

qwen2-5-3b-legal-indonesian

Qwen-2.5-3B-Indonesian-Legal-SFT

capsd-Qwen3-1.7B-Base-math_cap_b2000_s0

Llama_3_2_3B_Conversational_v5_SFT_10voicebot_disconnect_fixed_9april

Llama3.2_3B_UlyssesNER-BR

checkpoint-75

Qwen2.5-3B-Instruct-KAI

q-coder-br1

Qwen2.5-3B