Models

self-after-dark-3b

llama3_2_3B-practice-area-ft-125k-1epochs

Llama-3.2-3B-Base

LLaMa_3.2_3B_Catalysts

MediLlama-3.2

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer5_scoeff100_epoch10

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

Llama-3.2-3B-Instruct

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.1_alpha1_epoch10

Llama-3.2-1B-Processing-Phrase-Generator-11-19-New-System-Prompt-Validation-1119-0136

OctoThinker-1B-Long-Base

DigitalForensicsText2SQLite

Llama3.2-3B-gsm8k-fullft-atfter-ssft

nyaya-llama-3b-stage0-full

ReWiz-Llama-3.2-3B

DeepHermes-3-Llama-3-3B-Preview

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

Llama-3.2-1B-Instruct-APIGen-FC-v0.1

cogito-v1-preview-llama-3B

Malaysian-Llama-3.2-3B-Instruct

ReasoningCore-3B-R01

LLight-3.2-3B-Instruct

Dolphin3.0-Llama3.2-1B

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch10

GPT-5-Distill-llama3.2-3B-Instruct

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr5e-05_alpha2_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0001_beta30_alpha2_epoch10

pos_tofu_Llama-3.2-1B-Instruct_full_lr2e-05_wd0.01_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.1_alpha1_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr5e-05_layer10_scoeff10_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr4e-05_alpha5_epoch10

LLaMA3.2-1B-SFT

Llama-3.2-3B_safety

tofu_Llama-3.2-1B-Instruct_retain95

llama-3.2-MEDIT-3B-o1

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha5_epoch5

Llama-3.2-3B-Instruct-uncensored_SQLi

Veloce-1B

Llama-3.2-1B-Instruct-Complaint

OctoThinker-3B-Hybrid-Base

sonnet-llama-3.2-3b

Impish_LLAMA_3B