2-3B Parameter LLMs — Page 92

qwen3-1.7b-json-sft

Qwen3-1.7B-base-MED_0708

Qwen3-1.7B-base-MED

Spyfood-brain-v2

ToM-PBM-3B

alpaca-qwen25-finetuned

GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL

legal-ft-sft

capsd-Qwen3-1.7B-Base-math_ppl_b4000_s0

capsd-Qwen3-1.7B-Base-math_cap_b4000_s0

qwen2.5-3b-legal-grpo

Gemma-2-2B-Indonesian-Legal-SFT

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed1010

RLCR-0.25smCE-hotpot

qwen3-1.7b-a8_klreward-krew-k1-coef1e-4-mb4-eta100-bs256x5-n2

seccodeplt-qwen2.5-coder-3b-grpo-no-kl-real-detector-reward-v3

seccodeplt-qwen2.5-coder-3b-grpo-no-kl-real-reward-v2

Qwen3-1.7B-base-MED

MemoryDecoder-Qwen3-1.7B-biology

slm-trainer

kanha-kanha.ai-1.7b-pit-v1

kanha-kanha.ai-1.7b-qlora

gemma-2-2b-it

arkios-1b-chat

cs2881r-hw1

tofu_Llama-3.2-3B-Instruct_forget01_SimNPO

granite-3.3-2b-customer-support

tofu_Llama-3.2-3B-Instruct_forget10_PDU

llama3b-llama8b-er-v112-jb-seed2-seed2-openmath-25k

qwen2.5-vl-3b-ac-exp08-base-lr-1e-04-stage2-lora-epoch1

Main_MATH_3B_step_8

Qwen3-1.7B-base-MED_0401

Extended_Merging_Prob_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42

toolcalling-merged-demo

Main_fixed02_MATH_3B_step_1

qwen2.5-coder-3b-final-merged

Llama3.2-3B_Paper_Impact_code_SFT_1ep

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

toolcalling-merged-demo

QwenRolina-1.7B-base-LR1e5-b32g2gc8-order-batch-filtered

tft-benchmark-s3-tft-Qwen3-1.7B

armycadet_sample