4-5B Parameter LLMs — Page 15

Jan-v1-2509

MLPredic-4B

Affine-5HY6XuSFzMm49FbjBEbGSPnXo5vGoVUHy8HwYx5VXK5dC7Vn

short_paper_qwen_qwen3-instruct-4b_train_sft_train_para

GCCL-Medical-LLM-Qwen3-4B

affine-007

affine-finaltest-1

Qwen3-4B-chess-grpo-base-5000

daint_prod_ift_q3-4b_1N4n_16cdce0f_step-00100160

qwen_qwen3-instruct-4b_train_sft_train_para

dpo-qwen-cot-merged

qwen3-ft-test

Weak-Driven-Learning

AgenticCoder-4B

qwen3-4b-dpo-v0.03

dpo-qwen-cot-merged_v1

qwen3-4b-agent-v27

olympiad-curated-qwen3-8b-gc-5ep

qwen3-4b-multiturn-sft-16bit

Qwen3-4B-Instruct-2507-heretic

Jade4b

qwen3-4B-default-pubmed-labeled-5000-seq-2048

qwen3-4B-instruct-pubmed-final-answer-answer-only-artificial-5000

policyguard-4B-SS

Qwen3-4B-verienv-webjudge-filtered-action-tag-final

Qwen3-gabliterated-image-generation

Qwen3-4B-RP-V2

ReTool-Qwen3-4B-SFT-cold-started

qwen4b_secreason

Qwen3-4B-Thinking-2507-Esper3.1

OmniDimen-V1.5-4B-Emotion

qwen3-4b-question-gen

My-intelligent-true-qwen-RL

qwen3-4b-instruct-phishing-classifier

Qwen3-4B-Instruct-2507-MPOA

Hatshepsut-Qwen3_QWQ-LCoT-4B

Qwen3-4B-I-1209

DemyAgent-4B

s1-generator-critique-Qwen3-4B-Instruct-2507-20251214_200751

Refined-Gem-4B-Thinking

Qwen3-4B-Inst-CoTsft

olympiad-curated-qwen3-4b-thinking-generator-critique