1B Parameter LLMs — Page 160

Qwen2.5-1.5B-KTO-Finetuning

Manthan-1.5B-sft

ycomb2

indonesian-medical-qwen2.5-1.5b

phi-1.5-cross-lora-distilled-merged

cppo-g16-p0875

ball1

gemma-3-1b-medical-finetuned

tinyllama-medical1

chainlinkd-lora

unsup-Llama-3.2-1B-Instruct-only_mask_w_item_mesh

gemma-3-1b-medical-finetuned

gemma-1b-countdown-zero-shot

gemma-3-1b-it_Math_SFT

gemma-3-1b-it_Math_SFT

Qwen2.5-1.5B-reasoning-warmup

gemma-3-1b-it-Math-SFT-Math-SFT

CALYREX-1.5B-LoRA-Baseline

Gemma-3-1B-pt-is-SmolTalk

Gemma-3-1B-pt-sv-CPT-sv-SmolTalk

qwen2.5-1.5b-hgr-v2-5340-final

OpenThinker3-1.5B-checkpoint-375

TinyLlama-1.1B-Chat-moralogy-dpo-v4

strudel-refiner-1.5b-v1

gemma-3-1b-it-sst5-merged

gemma-3-1b-it-Math-SFT-0421-RS-DPO

IPA_Gemma_1B_merged

llama3.2-1b-Inst-antidote

nepali_legal_qwen_merged_4

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-8_merged

Minmax-TOFU-2

evolai-qwen2.5-1.5b-sn47-v2

Miner2

llama3.2-1b-Inst-somfmerge

ours_gemma_1b_output_dist_merged

llama3.2-1b-Inst-aaq

tta1

gemma-3-1b-loraplus-abstention

xd4

RLCR-1.5B-hotpot-rac-lr5e6

628801c9

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step450