Sub-1B Parameter LLMs — Page 126

sensor_v1_0.5B_fixed_s42

gemma-3-270m-linear-merged-trained-on-responses

aitestmodel-0625-002013

Qwen3-0.6B-Full-Finetuning-Thinking

ArgParser-v1

Qwen3-0.6B-Base

ecommerce-support-sft

rvr-exp21-s2_math-cot-correct

gemma-3-270m-MaxSlop

qwen2.5-0.5b-ca-homeowners-stage1

levantine-translation-qwen2.5-1.5b

summ_Qwen0b5_inst_cnnxsumsam

qwen-icmd

Qwen3-0.6B-GRPO-Finetuning

ATiNLP-qwen-debias-pandas-eng-small

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

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-8

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-10

Qwen3-0.6B

Qwen2.5-0.5B-Instruct_chat_dolly

Qwen3-0.6B-TL-SynthDolly-1A-E5

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

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

Qwen3-0.6B-Reverse-Text-JSD-10

day1-train-model

day1-train-model

Qwen3-0.6B-DA-SynthDolly-1A-E1

Qwen3-0.6B-EL-SynthDolly-1A-E1

Qwen3-0.6B-EL-SynthDolly-1A-E3

Qwen3-0.6B-GA-SynthDolly-1A-E3

Qwen3-0.6B-ES-SynthDolly-1A-E3

qwen2.5-0.5b-math-sft-new

20260411-190341-align-qwen-0d3d-2026-04-12-018-ob-correction

20260411-190341-align-qwen-0d3d-2026-04-12-022-aggressive-ob-dpo

maze-cuda-sft-5000-qwen2.5-0.5b

qwen3-05b-full-test

cs224r-default-sft

router-sft-smoke-merged

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

BoyBarley-V27-Pro-Buddy

FinSense-Wealth-Manager-0.5B

cs224r-sft-full-v1