Sub-1B Parameter LLMs — Page 114

TASX-Cmd-0.5B

general-kd-Qwen2.5-0.5B-Instruct-ber-5000

opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-500

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-1000

opd_gsm8k_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

sql-debug-agent-qwen25-05b-grpo-wandb-continue-v2

Qwen3-0.6B-PJ-100K

Qwen3_0.6b_Opus_4.6_v1

filter-0.5B

FinSense-Wealth-Manager-0.5B

scbe-coding-agent-qwen-merged-coding-model-v2

mini-1.0

itmo-nlp-hw6-qwen2-5-0-5b-abliterated

cricket-captain-qwen3-06b-merged

PBoC-rrk-ctq-v1-epoch-2

Qwen3-0.6B-student-refusal-badnet-seqkd

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-5000

QwenRolina3-06B-base-LR1e5-b32g2gc8-AR-order-batch

qwen3-0.6b-sciq-v2

qwen2.5-0.5b-countdown-sft-optimal1

qwen2.5-0.5b-bigmath-grpo-merged

db-surgeon-qwen3-0.6b-grpo

PBoC-rrk-ctq-v1-epoch-3

deepsentinel-overseer-small

qwen2.5-0.5b-4-bazi20260426

Qwen3-0.6B-finetuned-astro_horoscope_use_FA2

qwen2.5-0.5b-ifeval-pure-kd

qwen2.5-0.5b-ifeval-halfepoch-sft

translator_3e-05_8

qwen2.5-0.5b-ifeval-mixed-kd-alpha05

Qwen2.5-0.5B-trit-uniform-d3

Qwen2.5-0.5B-trit-uniform-d4

BoyBarley-V28-Pro-Buddy

sql-debug-agent-qwen25-05b-grpo-wandb-best

Kimi-K2-Instruct-DRAFT-0.6B-v3.0

Qwen3-0.6B-heretic

Qwen3-0.6B-g_general_reward-seed_0

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens_w3-seed_0

legal-chatbot-grpo

test

qwen2.5-0.5b-dora-abstention