Text Generation Models — Page 341

torchtune_1B_lr1.5e-5_2epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

EchoLLaMA-1B

torchtune_1B_lr1.5e-5_3epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Llama-3.2-1B-Instruct_AllDataSources_5e-05_constant_512

Grogros-dmWM-Llama-3.2-1B-Instruct-M-A-O-d4-a0.25-learnability_adv

1b-sft-bio

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-OWTWM2-wmToken-d4-10percent

Priapus-3.2-1B

LocalAI-functioncall-llama3.2-1b-v0.4

Llama3.2-TaiPhone-1B-Instruct-v0.1

tfa_output_2025_m05_d10_t19h_57m_34s

Llama-3.2-1B-Instruct_sum_KTO_40k_2_1ep

pos_tofu_Llama-3.2-1B-Instruct_full_lr2e-05_wd0.01_epoch5

gemma-2-2b-it_RMU_s400_a1200_layer11

gemma-2-2bit-quantised

gemma-2-2b-it_RMU_s400_a100_layer3

gemma-2-2b-it_RMU_s100_a300_layer7

gemma-2-2b-it_RMU_s200_a100_layer7

gemma-2-2b-it_RMU_s100_a1200_layer3

gemma2_2B_it_greek_007

gemma2b_full_ft_dare

gemma-2-2b_RMU_cyber-forget-corpus_s400_a300_layer7

gemma-2-2b_RMU_s400_a500_layer7

sft_backdoors_Gemma2-2B_code3_dataset_experiment_19.1

SFT_peft_DARE

delta_safe_plus_sft

Vera-Instruct

gemma-2-2b-it-star-mixed_direct-OF-final_v2_10-2-3Rounds-iter-1

17718_sft_32_sh

gemmadpo3

gemma-2-2b-it-sft-dare

17718_sft_8

gemma-2-2b-instruct

gen1

base_2d_random_green_normal_first_quadrant_red_no_preamble_v2_20250602_152147_20250602_165416

task2_2d_random_common_words_positive_emotions_v3_5plants_proxy_20250603_180233

task2_2d_random_common_words_positive_emotions_20250603_142225

task2_2d_random_common_words_positive_emotions_v2_5plants_proxy_20250603_174751

torchtune_1B_lr1.5e-5_6epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

Qwen2-0.5-Instruct

SparkleRL-7B-Stage2-aug

ms3.2-24b-longform