2-3B Parameter LLMs — Page 94

qwen2.5-3b-legal-merged

llama32-3b-redo-sft

QThink-Qwen3-1.7B-AIME2025

claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed1010

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed51485

qwen2.5-3b-legal-id-grpo

alexk

qwen3-1.7b-a9_dapo-dapo-noKL-clip0.2-mb4-eta100-bs256x5-n2-r3

qwen3-1.7b-a8_klreward-krew-k1-coef1e-2-mb4-eta100-bs256x5-n2

claimtrace-smoke

Qwen3-1.7B-base-MED

qwen3-1.7b-digestive-coach-n478

qwen3-1.7b-digestive-coach-n275

kanha-kanha.ai-1.7b-grounded-qlora-v1

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed10

Qwen3-1.7B-base-MED

tofu_Llama-3.2-3B-Instruct_forget05_UNDIAL

legal_retrieval_llama_3_2_3B_8192tokens

Qwen2.5-3B-GRPO-Staleness-8

llama3b-llama8b-er-v110-jb-seed2-seed2-sharegpt-50k

qwen2.5-vl-3b-ac-exp08-world-model-stage1-full-epoch3-stage2-full-epoch0.25

qwen2.5-vl-3b-ac-exp08-world-model-stage1-full-epoch3-stage2-full-epoch0.5

my_model_p

Extended_Merging_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42

Qwen2.5-3B-RM8B

Main_fixed02_MATH_3B_step_2

FAME_GA_llama32-3b-instruct-qa

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint75

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint50

Phi-2-DPO

Stack-X-Ultimate

CodeRM-GRPO-Selection-1.7B

qwen3-1.7b-fft-coding

pm-ops-grpo-Qwen3-1.7B-triage-v4

tft-benchmark-s5-tft-Qwen3-1.7B

Qwen2.5-3B-INST-Math

Qwen2.5-3B-Instruct-SMS-SFT

olympiads_Main_fixed_BaseAnchor_3B_step_7

min0-translator-v1

cnk12_Main_fixed_SFTanchor_3B_step_2

sft-qwen3-1.7b-budget-router-smoke

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated