1B Parameter LLMs — Page 164

deal-extractor-1.5b

Qwen2.5-Math-1.5B

FAME_PO_llama32-1b-instruct-qa

model_sft_resta

ds1p5b_no_if-global_step_400

my-cool-ai

model_sft_resta

AceInstruct-1.5B-Gensyn-Swarm-loud_powerful_dolphin

Qwen2.5-Sex

qwen2_5_1_5b-abstract-finetuned-ep2-b4

model_sft_dare_resta_0.5

gemma-3-1b-medical-finetuned

jailbreak-attacker-l2

demosample

gemma-3-1b-it_Math_SFT

CPO_hh-seed5

DPO_hh-seed2

FAME_GA_llama32-1b-2p5-instruct-qa

FAME_PO_llama32-1b-2p5-instruct-qa

FAME_GD_llama32-1b-1p25-instruct-qa

FAME_GD_llama32-1b-10-instruct-qa

tinyllama-medquad-merged

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

Qwen1.5-1.8B-fSWIFT-js-ite2

PureRL-1.5B-v5-06-uppl

qwen-rag-indonesia

qwen_instruct_codereview-merged

Ouro-1B-Base

cx-filler-model

Qwen2.5-1.5B-Instruct-EASE

LFM2.5-1.2B-Instruct-Korean-Opus-4.6-Distill

gemma-fyp-mindease

Qwen2.5-1.5B-Instruct

luciole-ablation-1B-en0.66-fr0.33

ecomm-db-stage2-sft-merged

sarvix-multilingual-1

harry_phi_to_unlearn

resume-parser-qwen-1.5b-kaggle-country-school

ppo-qwen2.5-1.5b-alfworld-step20

Teacher_r14_train_gptmini-Qwen2-5-1-5B-seed896

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-seed51485

claude_stagger_cur1to7_perblock5-Qwen2-5-1-5B-seed51485