Models

Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-5e5-100

ver_partial_ft_model_meta-llama_Llama-32-1B_checkpoint-4224

dm-llama3.2-1BI-OWTWM-OWT-Al4-WT-v13-meta-OWT

llama-3.2-1B-CEH_v10

Llama-3.2-1B-uk-ext

torchtune_1B_lr1.5e-5_14epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

finetuned_llama3.2

Llama-3.2-1B-Instruct-zh-de-ja-linear

dm-llama3.2-1BI-OWTWM-OWT-Al4-WT-ran1-meta-OWT

finall_sup_vcs

llama1B_OB75

final_model_mcq

Llama-3.2-1B-Instruct_sum_DPO_10k_1_3ep

Llama-3.2-1B-Instruct_ifeval-like-data_cluster9

Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat-PT2

RS_GT_SFT_1B_iter2

Llama-3.2-1B_AllDataSources_5e-05_constant_512_flattening

Qwen2.5-0.5B_new_2

Llama-32-1B-Instruct-ft-citation-ensemble-label

dm-llama3.2-1BI-OMI-Al4-OWT-ran1-meta-OWT

llama8b_normal_1B-alpaca_3

llama-3.2-1b-it-Intro-Physics-Problem-Extractor

test_mcq_vcs2

ours-llama-3.2-1b-gsm240k

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-wmToken-d4-0percent

Llama-3.2-1B-Instruct-LoRA-Merged_small

torchtune_1B_lr1.5e-5_9epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

torchtune_1B_lr1.5e-5_11epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

llama3_DPO_New

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_64_32_0.05_16CLINICALe3c-sentences_tag

llama3_DPO_100

llama8b_SEND_1B-codesearchnet-2

testing_medium_v0

Llama-3.2-1B_AllDataSourcesClinical_0.0002_constant_1024_paper

3_random_MQA_llama_model

llama-3.2-1B-with_labels

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B_3x3_mix_position

av-triple-ext-llama-3.2-1B-merged-4bit-qlora

hdjhdhdhdhehewj

sungyoonaimodel2

llama8b_normal_1B-codesearchnet_3