Models

Llama-3.2-1B-Instruct_sum_DPO_40k_1_3ep

Llama-3.2-1B-Instruct_sum_DPO_1k_1_1ep_4bit

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct_sum_DPO_40k_2_3ep

star_plus-finetune-llama-3.2-1b-gsm8k-step-1

dmWM-LLama-3-1B-Harm-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25-DPO

ScienceLLaMA-1b

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40.0k_1_1ep

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr2e-05_beta0.1_alpha2_epoch10

LLAMA-3.2-1B-IDENTITY

llama3-finetuned-Latest_f16

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_2_2ep

11_layer_MQA_llama_model

pos_tofu_Llama-3.2-1B-Instruct_retain90_forget10_bio_lr5e-05_wd0.01_epoch5

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10k_1_2ep

pos_tofu_Llama-3.2-1B-Instruct_retain90_forget10_bio_lr1e-05_wd0.01_epoch10

llamainstructgoodendings

q487

llama3.2-3b-dpo-mini

one2

aifactory-c9

EcomGen-Llama3.2-3B

GRMR-V3-L1B

jCool10-LLaMA3-VietQA-3B-merged

Psychologist-3b

Firefly-V2-abliterated

Llama-3.2-3B-Instruct-AMPO-V1

Llama-3.2-3B-Instruct_unsloth_w_new_merged

SmolLM3-SFT-Second-Round

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr5e-05_b3.5_a1_d1_g0.25_ep5

trainorder

sadtest

llama3.2-bank-ft-LF

llama-3.2-3b-distilled-ctba

llama-3.2-3b-distilled-vpi

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr1e-05_beta0.1_alpha5_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff10_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr1e-05_beta0.1_alpha1_epoch5

Llama-3.2-1B-Instruct-unsup-crf-full-weight-merged

Llama-3.2-3B-Instruct-3-sfand-cause-effect-model-lora

llama-sft-proj-layers-shmid

Llama-3.2-1B-Instruct-C_M