Sub-1B Parameter LLMs — Page 121

Qwen2.5-0.5B-Math-SFT-1024

symfony_ai_maker-V0.7.1-Qwen3-0.6B-16bit

lead-architect-compliance

Qwen3-0.6B-Final-Merged16bit

symfony_ai_maker-V0.5.1-Qwen3-0.6B-16bit

akeel-4B-lora

study-buddy-final

University_of_Abuja_AI

debatefloor-grpo-smoketest

zeroVuln

qwen2.5-0.5b-grpo-arithmetic

opd_medical_qwen3-0.6b_frozen_teacher_forward_kl

qwen2.5-0.5b-squad-finetuned-houssam

confundo-opinion

rloo-a0-baseline

rloo-c2-replay

rloo-d1-replay

rloo-a2-baseline

magnusbot

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-flapping_foxy_beaver

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-mammalian_roaring_worm

environment_test

Qwen2.5-3B-GRPO-3_3_8_6k

qwen3_0.6b_gsm8k

geode-beryl

qwen3-05b-full-test

Qwen3-0.6B-Gensyn-Swarm-feathered_wiry_anteater

qwen2.5-0.5b-sft-deepmath

hellqwen

distillm2-sft

Qwen3-0.6B-Chat-SFT-ultrachat3k-DPO-argilla6k

Qwen3-0.6B-Reverse-Text-SFT

qwen3-0.6b-4bit-sft-only-400-full-16bit

qwen3_0.6B_segmenter

Qwen3-0.6B-finetuned

qwen3-0.6b-lora-256-256-lr-0.0001-bs-256

cook-assistant-Qwen3-0.6B

grpo_baseline_medical_qwen3-0.6b

Qwen2.5-0.5B-Instruct-math

Qwen3-0.6B-proposer-grpo

medqa-hindi-qlora

anon-0.6B-SFT