Sub-1B Parameter LLMs — Page 113

Qwen2.5-0.5B-Instruct-linearexpression

sft_ft

halluci-mate-v1b

qwen2.5-0.5b_em_badmed

Gurt_v1

S1-lite

qwen3-0.6b-capybara-smoke

focus-patrol-qwen2.5-0.5b-v7

axeai_m_0.1

LFM2.5-350M-Tool-Calling-Merged-v3

LFM2.5-350M-abliterated

kulyk-en-uk-grpo

Qwen2.5-0.5B-Instruct-BNB-8bit

Qwen2.5-0.5B-Instruct-rt

exp1

levantine-translation-qwen2.5-1.5b

llm-test

Qwen1.5-0.5B-Chat-edcastr_JavaScript-v1

Qwen2.5-0.5B-Instruct_chat_dolly

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-7

Qwen3-0.6B

Qwen2.5-0.5B

day1-train-model

Qwen2.5-0.5B-Instruct_chat_dolly

wordle-lora-20260324-163252-sft_full_smoke_06b_autofix

grpo-qwen-gsm8k

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

sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4

Qwen3-0.6B-GA-SynthDolly-1A-E8

Qwen3-0.6B-EL-SynthDolly-1A-E8

qwen25-0.5b-codeforces-sft-budget-merged

SupplyChain-Qwen2.5-0.5B-FP16

qwen3-0.6b-gpt4-distilled-v2

general-kd-Qwen2.5-0.5B-Instruct-ber-50000

general-kd-Qwen2.5-0.5B-Instruct-npi-4504

embed_1lakh

1lakh_embed

day1-train-model

Qwen3-0.6B-FarmifAI1.0

Qwen2.5-0.5B-Instruct-CrashCourse-dropout

bold_formatting-Qwen3-0.6B-OURS_self-seed_0