4-5B Parameter LLMs — Page 35

Affine-2m5d-5FZNvCq99HQubesSSKumcEfmXckRhHadCw7sPf6Zq9gUnoxr

Qwen3-4B-Instruct-2507-imagegame

math_RL_LS

Qwen3-4B-Instruct-2507-Car-50-GPT41Tea-notROnly-Merge-6e-5-Q4-32768-1633Feb04

affine-hoh-5FjZYkzVtjQH6q2qefVePKFr7h1cwthpDEA2NMy6BGopDi9g

PiG-v0-dpo

test

Qwen3-4B-MHS-1.1

dpo-qwen-cot-merged-from-sft-adapter-38-1

dpo-qwen-cot-merged.ver0

C03-none-distilled-qwen3-4b

distillation-2

qwen3-4b-struct-exp77

qwen3-4b-structeval-sft-v4-lr2e5-merged

Qwen3-refual

qwen3-4b-dpo-v0.01

Luma-base

Prism-Questioner

LocoOperator-4B-Swift-Balanced

qwen3-4b-gsm8k-sft

qwen3-4b-kairis-fast-r16

Tema_Q-X-4B-Thinking

Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL

Qwen3-4B-CoderForge-SFT-weighted

m4b_print72

qwen3_4b_baseline_v2_solver_v2

qwen3_4b_baseline_v2_solver_v3

qwen3_4b_baseline_v2_solver_v4

Qwen3-4B-CoderForge-SFT-baseline-epoch2

Qwen3-4B-CoderForge-SFT-baseline-epoch3

qwen3_4b_baseline_v2_solver_v5

qwen3_4b_vdrop75_v2_solver_v1

qwen3_4b_vdrop75_v2_solver_v2

qwen3_4b_vdrop75_v2_solver_v5

qwen3_4b_vdrop85_solver_v5

sft_qwen3_4b_tmax_4node2203

trial0322-4b-DAPO-vd-lr5e-6-kl0-g4-distill0.1-removenone-groupmean-8192-step134

Qwen3-4B-Science

Openmed-icd10-rl-4b-lora-super-train-base

csrsef-instruct-20260325T021216Z-it01-pubmedqa

qwen3_4b_sudoku_one_act_rl_default_epoch1

qwen3_4b_sudoku_multi_act_rl_epoch1