Qwen 2.5 Models — Page 62

Qwen2.5-3B-GRPO-3_5_8_6k

gORM-14B-4-merged

big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-global_step_20

Achillees-14B

kim-multilang-coder-qwen2.5-coder-32b

SDRL-freq-Qwen2.5-3B-icml-self-debate-exp-majority_n4_l2048-DAPO_n8_bs256_long8-step200

tournament-tourn_2cd19ba0c3b9771f_20260618-33a3f0f4-214c-4776-a409-bf8ba3e0726e-5GU4Xkd3

Heretic-Dolphin3.0-Qwen2.5-3b

v1-14b-software-docsqa-seed2

v1-3b-software-docsonly-seed3

v1-3b-software-docsonly-seed2

v1-3b-planets-docsqa-seed2

v1-14b-people-docsqa-seed3

v1-3b-software-docsqa-seed1

MiA-Gen-14B

ee_qw14_grpo

Caller

r

SiriusAI-Text2SQL-32B-v3

qwen25-32b-rukun-merged

limo_32B

lamarckvergence-14b-tensopolis-v1

drishti-smart-x1

Qwen2.5-32B-Instruct-ftjob-4b351f79e129

Qwen2.5-32B-Instruct-ftjob-6abcccb0642a

requirements-brain-v6-merged

yosa-gin002

qwen25vl-7b-invoice-extractor

Qwen2.5-Coder-3B-SFT-WebCode

qwen2.5_3b_instruct_finetuned

HuatuoGPT-Vision-7B-Brainseg-SFT-224-v2

qwen-coder-insecure

unified-model-stage1-5

WebSailor-32B-SFT-v11-merged

cyberguard

support-agent-qwen25-3b

countdown-qwen2.5-3b-grpo-mi300x

SDRL-baseline-DAPO-Qwen2.5-3b-self-debate-baseline-dapo-n8-bs256-long8-step200

SDRL-rand-Qwen2.5-3B-icml-self-debate-ablation-random_n4_l2048-DAPO_n8_bs256_long8-step200

Qwen2.5-14B-Instruct-all-q_comb

v1-3b-people-docsonly-seed3

v1-3b-people-docsonly-seed2