Sub-1B Parameter LLMs — Page 122

Qwen3-0.6B-Base-CPT-Math

gkd-qwen-2.5-0.5b-base_v2_eff32

sft-merged3

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

gkd_gsm8k_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

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-5000-2000

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-1500

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

Qwen2.5-0.5B-Instruct-abliterated

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

Qwen2.5-0.5B-GRPO-KL-math-reasoning

qwen3-0.6b-pandora-tools-no-embedd

Qwen3_0.6b_Opus_4.6_v1

Qwen3-0.6B

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-3500

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

symfony_ai_maker-V0.8.1-Qwen3-0.6B-16bit

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

hanoi-router-qwen25-05b-v6

qwen3-0.6b-sciq-v5

qwen2.5-0.5b-sft-countdown

qwen3-0.6b-sciq-v4

maze-cuda-sft-9x9-qwen2.5-0.5b

qwen3-0.6b-pandora-tools

trained_model

Qwen3-0.6B-Base-CPT-Math

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

qwen-sft-countdown

Qwen3-0.6B-Final-Merged16bit

PBoC-rrk-ctq-v1.01-epoch-1

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

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

qwen2.5-0.5b-loraplus-abstention

trustfinance-qwen0.5b-dpo

ipo-finetuned-qwen2.5-0.5b

confundo-opinion

cs224r-sft-tags-proof-backtrack-v5-eos

qwen3-0.6b-capybara-1step

qwen3-0.6b-capybara-smoke