4-5B Parameter LLMs — Page 27

test16-dpo

Qwen3-4B-rft-webshop

qwen3-4b-sft-v5h-hybrid-merged

qwen3-4b-v2-exp26-dpo

qwen3-4b-v2-exp28

qwen3-4b-agent-v13

parser_model_ner_3.98

QwenDatacenter

medgemma-1.5-4b-it

dpo-qwen-cot-merged20

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

Affine-01-5EALnKDFv8qkqERMbTFoZWz2BBofuti1zRuvcRq1JCT81rdJ

test12-dpo

amity-sigma-thinking-v3r

qwen3-4b-multiturn-sft-16bit

tmax-qwen3-4b-sft-20260316-100k-asst-loss

Qwen3-4B-Instruct-Conscious

sinhala-qwen3-4b-lora

harper-valley-qwen-merged_sft_ckp_100

Qwen3-Embedding-4B-IC

reward-hacking-sft-10-percent-Qwen3-4B-Thinking-2507

gemma3-4b-mbti-chat-mind

qwen3-4b-thinking-2507-q3_k_m

tau-max-retail-v1

gemma-3-4b-it

affine-comp-02

affine-exciter-3

agentic-sokoban-Markov_qwen3-4B-5e-6_gt-SFT_4k

Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_2048_epoch_1

math_acc_4B

arc-abs-sft-no-oracle-lr5e-6-ep1-0104

Affine-first

agentic-sudoku-NoStateTrans_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

qwen3-4b-dpo-hh-rlhf-reversed

agentic-sudoku-NonMarkov_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

Affine-5ED8SHB9ThQTwwtc9tKHkHmaYstpUiehBdbu1BB1drjq3uth

rl-4b-arc-abstractions-judge-unnorm-nothink-deltarerun-step180-0116

qwen-arc-abs-gpt5.2-sft-fewshot4-1epoch-icmlpaper-0125

Qwen3-4B-Instruct-2507-GRPO-merged

fff-ooo

qwen-arc-abs-gpt5.2-sft-1epoch-icmlpaper-0125

qwen3-4b-instruct-meta-GRPO-2