2-3B Parameter LLMs — Page 103

general_knowledge_model

fol-v01-origin-qwen2.5-3

Llama-3.2-3B-Instruct-EN-SynthDolly-r16alpha128-E8-S73

Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged

AutismWenLLM

qwen2.5-3b-gec-v2

qwen2-5-3b-legal-finetuned-grpo

qwen3-1.7b-fft-dpo-4epochs

math_model

Llama-3.2-3B-ThinkSFT

VibeThinker-3B-MLX

Qwen3.5_VL_2B_minor

Qwen-Indo-SFT

qwen3-1.7b-json-sft

Firefly-V3.2-1-dontdownload

Occam-2B-CCoT

idp_invoice

RLCR-0.05smCE-hotpot

RLCR-0.00005smCE-hotpot

finetuninggg

shadow-ai-3b-full

Qwen2.5-3B-ProxyMath-Merged

Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed51485

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed896

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

qwen3-1.7b-a7_current_kl-curKL-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2

qwen3-1.7b-a6_k3_center-k3-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2

qwen3-1.7b-a20_seqmean_center_16k-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

qwen-1.7b-sft

2026-05-o-b0p5-a0p5-gc0p5-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b-last

qwen3-1.7b-article-usage-micro-coach

qwen3-1.7b-digestive-coach-n137

qwen_reasoning_16bit

Qwen3-1.7B-OPD-step120

gemma-2-2b-it_RMU_s200_a300_layer7

gemma2-2b-base-filtered-geometry-keep-0.7

Teacher_r14_train_claude-Qwen2-5-3B-Instruct-seed51485

qwen3-1.7b-stance-matrix-mtcsd-qlora