1B Parameter LLMs — Page 26

qwen2.5-1.5B_Bn

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer5_scoeff10_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr2e-05_beta0.5_alpha1_epoch5

tinyllama-sentiment-analyzer-en-v0.1

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr5e-05_beta0.05_alpha1_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.5_alpha5_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha5_epoch10

Llama-3.2-1B-Instruct-FFT-coder-python

neg_tofu_Llama-3.2-1B-Instruct_retain90_lr1e-05_wd0.01_epoch5

smartyplats-1.1b-v2

Llama-3.2-1B-Aegis-SFT-DPO

neg_tofu_Llama-3.2-1B-Instruct_retain90_lr1e-05_wd0.01_epoch10

TinySwallow-1.5B-Instruct

Orpo-Llama-3.2-1B-15k

llama-3.2-1b-lewd-mental-occult

dmWM-llama-3.2-1B-Instruct-KGWB-OWT_WMBoundary-OWT-WB-v3

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr1e-05_beta10_alpha1_epoch5

WiroAI-Finance-Qwen-1.5B

6dcf0f35

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha5_epoch5

gras1

LLAMA-3.2-1B-OpenHermes2.5

qwen2.5-1.5b-general-forged

Open-RS1

Qwen2.5-1.5B-Instruct_ifeval-like-data_origin

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.1_alpha5_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha5_epoch10

block-q-sharp_ds-distilled-qwen-1.5b-ppo-kl-1e-4-ec-0.001-16384_actor

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha1_epoch10

Llama-3.2-1B-it-chinese-kyara

orca_mini_v9_5_1B-Instruct

Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaPoison

Llama-3.2-1B-Instruct-distillation-SecretSauce-5.0-AlpacaPoison-5e5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch5

Qwen2.5-Math-1.5B-16k-think

Qwen2.5-1.5B-Open-R1-Distill

Qwen2.5-RCA-1.5B

Qwen2.5-1.5B-Instruct_gsm8k

qwen2.5-1.5B-india-finetuned

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha1_epoch10

LUFFY-Qwen-Math-1.5B-Zero

titulm-llama-3.2-1b-v1.0