Sub-1B Parameter LLMs — Page 138

grpo_baseline_medical_qwen3-0.6b

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

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

v10_fixed_s1

final-d2-0.6b

rvr-exp21-s2_math-cot-correct

gemma-3-270m-cpt-spm-2K-5y

qwen2.5-0.5b-instruct-infosft-tooluse

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

instruct_text_62842f442b79e6dbfd50

checkpoints-best-qwen14-chi

Qwen2.5-0.5B-Instruct-LLM

sger-lfm2.5-name-matching

zay-instruct-0.5B-2

Qwen3-0.6B-Reverse-Text-SFT

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

geode-beryl

lead-architect-compliance

qwen2.5-0.5b-sft-deepmath

OA_Qwen3-0.6B-Base_lr-1e-07_e-5_s-0

ipo-countdown-qwen2.5-0.5b

bm2_cs7_fixed_v1

rloo-c2-replay

rloo-test-gemini

mini-qwen3-0.5b

Qwen3-0.6B-Reverse-Text-SFT

FunctionGemmaBlindStick

rvr-exp21-s2_math-intermediate-correct

agentic-search-sft-0.6B

qwen2.5-0.5b-instruct-infosft-science

qwen2.5-0.5b-instruct-sft-science

business-chatbot-qwen2.5

checkpoints-first-gemma12b-chi-sampled

q0.5_prunne_fp16

LFM2.5-350-Fune-tune

checkpoints-first-gemma12b-clean-fr

environment_test

qwen3_0.6b_gsm8k

akeel-4B-lora

distillm2-sft

debatefloor-grpo-smoketest

zeroVuln