2-3B Parameter LLMs — Page 23

Qwen2.5-3B-GRPO-3_13_math

EvoNet-3B-V6

Parkwave-BOT

akron-field-396hz

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_42_rule

teacher_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

mental_RL_0.7_global_step_39

FoxyzGPT-X1.1-1.7B

seva-sarathi-intent-qwen3-1.7b

Qwen3-1.7B-base-MED

qwen3-1.7b-unslop-good-lora-v1

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

Main_fixed_MATH_3B_step_9

Qwen3-1.7B-Base_dsum_3_6_0p5_0p0_1p0_grpo_dr_grpo_42_rule

Main_MATH_3B_step_7

Phi-4-mini-instruct

very_fine_tuned_gemma2

gemma_munganga-pawa

3400_mcq

gemma-2-2b_RMU_cyber-forget-corpus_s200_a300_layer3

gemma-2-full-ft-total

gemma-2-2b-it-pm-ep1

17718_sft_64_sh

SFT_fft_Resta

Llama-3.2-3B-NuminaQA

Qwen2.5-3B-Open-R1-GRPO-math-selected-default

verl_sft

easy-8k-med16k

owmqa_none

phi4-mini-dolly-15k-mlx

qwen2.5-3b-vietnam-legal-logistics

devspeedllm-ft-v0.0.6

Qwen3-1.7B-finance

Nix-1

ppo_sgd_qwen3_1.7b_1e-2_critic_adamW

OpenRS-DR_GRPO_dra-qwen2

Llama-3.2-3B-Instruct-AMPO-V0-5

grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2

Qwen_3b_medical_o1_reasoning

Qwen3-4B-GRPO-MathsFT