1B Parameter LLMs — Page 27

Llama-3.2-1B-Instruct-FineTome-100k

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr2e-05_alpha2_epoch10

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

Qwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFT

Llama-3.2-1b-bnb-4bit-python

has3

sd-seer-tinyllama

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha2_epoch5

neg_tofu_Llama-3.2-1B-Instruct_retain90_celeb10_bio_lr1e-05_wd0.01_epoch10

Llama-SmolTalk-3.2-1B-Instruct

FineTome-v1.5-Llama3.2-1B-1007

Llama-3.2-1B-Instruct-LoRA-Merged_wo_tokenizer

LLaMa_coder_base_sft

Llama3.2.1B.BaseFiT

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr5e-05_alpha5_epoch5

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

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff10_epoch5

AceInstruct-1.5B-Gensyn-Swarm-toothy_crested_snail

qwen2.5-1.5b-seq-dspo-sgd-linear

BerkeliumGPT-Coder-3b

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr1e-05_beta0.1_alpha5_epoch10

neg_tofu_Llama-3.2-1B-Instruct_retain90_lr2e-05_wd0.01_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr1e-05_alpha2_epoch5

dmWM-llama-3.2-1B-Instruct-OMI-Al4-OWT-d6-a0.16-v4

dmWM-llama-3.2-1B-Instruct-KGWB-OWT_WMBoundary-OWT-WB-v2

Llama-3.2-1B-Instruct-activation-SecretSauce-3.0-AlpacaPoison-5e5

neg_tofu_Llama-3.2-1B-Instruct_retain90_lr4e-05_wd0.01_epoch10

M-project

Qwen2.5-1.5B-Open-R1-GRPO-FC

DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic

Yumo-nano

Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE

Qwen2.5-Coder-1.5B-Merged

tinyllama-fake-news-detector-en-1.5T-v0.1

MiniThinky-1B-Llama-3.2

Llama-Deepsync-1B

Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaRefuseSmooth-sauce2lr

Dhanishtha

sleeper-proxy-tinyllama-1.1b

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

ADELIE-SFT-1.5B

pos_tofu_Llama-3.2-1B-Instruct_full_lr1e-05_wd0.01_epoch5