2-3B Parameter LLMs — Page 31

Qwen2.5-3B-Instruct_old_sft_alpaca_003

qwen2.5-3b-icd10-top50-multi-task

OctoThinker-3B-Short-Base

qwen2.5-3b-instruct-motion

furryvpntrash

qwen3_1.7b_psyscam_romance_ephishllm

qwen3_1.7b_romance_ephishllm

OncoCareBrain-GPT

Qwen3-Grand-Horror-DARK-Child-1.7B

pcos-fertility-llama3-8b

Llama-3.2-3B-Pure-RP

Qwen3-1.7B-tamil-16bit-Instruct

d1_v2_qwen_3B_ep2_shuffled_8192

qwen3-1.7b-amr-vi-sft

Qwen2.5-3B-Urdu-Ultimate-Poet

Qwen_3B_Instruct_2_lvl12_less_steps

Qwen2.5-3B-Math-Verifier-FullData-v2.0

Qwen3-1.7B

gemma-2-2b-Distillation-gemma-2-27b-it

qwen2_5_3b_anton

backdoor-model-1

GeneralChat-Llama3.2-3B

Qwen3-1.7B-SFT-s1K-lr2eneg05

SFT_Qwen2.5-3B-Instruct_MATH

qwen2.5-3b-calendar-agent

HiTOP-Llama-3B_4bit

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_1p0_0p1_1p0_grpo_sapo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_1p0_0p0_1p0_grpo_dr_grpo_42_rule

mental_RL_0.7_best

gemma-2-2b

Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_mix_alt_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-base-MED_0325

armv8mac_to_riscv_qwen25coder_3p0b_full

armv8mac_to_x86_qwen25coder_3p0b_full

Llama-3.2-3B-Instruct-C_M_T-AUX_CT2_CE_EE

Extended_GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

toolcalling-merged-demo

toolcalling-merged-demo

Main_fixed_MATH_3B_step_8