Models

LLAMA-3.2-1B-IDENTITY

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0001_beta3_alpha2_epoch10

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

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr2e-05_beta0.05_alpha1_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff100_epoch5

GRMR-V3-L3B

Llama-3.2-3B-Instruct-Football_Match_History

Llama-3.1-8B-lora-step30

Llama-3.1-8B-Instruct-SFT-CoT-short

Llama-3-Base-8B-SFT-SimPO

pruned-pruned-llama3-8b-instruct-wanda-0.5-unstructured-mc4-de-42

Meta-Llama-3-8B-Instruct-GRPO-injected-alpaca-2000-checkpoint-2000

finetuned_modelo9

llama2-fine-tuned-dolly-15k

email-categorisation-llama2-7b-peft

Llama-2-7b-chat-mqa

WenyanGPT

gras14

trt2

tinyllama-katakana-converter

Llama-3.2-3B-Instruct-VMPO-V1

llama-3.2-1b-instruct-augmented

meta-llama-Llama-3.1-8B-Instruct-pisanitizer-squad_v2-llm-judge-42-20260108-1706

short_paper_llama_llama3.1-8b_train_sft_train_para

SmolLM3-SFT-Second-Round

grpo_sgd_llama3p1_8b_3k-seqlen_momentum_0p9_1e-3

ReasoningCore-1B-r1-0

m199

llama-3.2-1b-redteam_ift

Llama-3.2-3B-Instruct_old_sft_alpaca_001

Llama-3.2-1B-Instruct-unsup-crf-full-weight-no-adapters

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.1_alpha5_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer5_scoeff10_epoch5

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

Pite12-coder

baseline_rm_1_1150_merge

unsup-Llama-3.2-1B-Instruct-datav2

Denglish-8B-Instruct

llama3.2.3B_cognitive_distortions_16bit

llama-sft-proj-layers-shmid

llama-sft-baseline

Llama-3.2-1B-Instruct-C_M_T_CT_CE_CM