Models

llama3.2-1b-oasst2-33k-ja

E1

reach

Llama-3.2-1B-betadpo

Jaja-medium-v1

llama3.2-1b-neuspell

llama3-finetuned-best

dermai-v3

13_layer_GQA4_llama_model

rclama32-merged-final

Grogros-dmWM-llama-3.2-1B-Instruct-LucieFr-Al4-OWT-d4-a0.2-learnability_adv

torchtune_1B_lr1.5e-5_0epoch_full_finetuned_llama3.2_millfield_241227_meta_before_user_15epoch

my-v0

archer-llama3.2-1b-full

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

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-v3

main-train

llama-ina_cbg

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

16_layer_GQA4_llama_model

llama32_1bi_stdsft_rs0_1_5cut_e2

llama3-finetuned-Best_f16_Accurate

Llama-3.2-1B-Instruct_sum_KTO_40k_2_3ep

s801

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_32_32_0.05_16CLINICALe3c-sentences_tag

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-OWTWM2-wmToken-d4-5percent

Llama-3.2-1B-Instruct_sum_PPO_Skywork_80k_2_3ep

DPOLlama-3.2-1B-Instruct_sum-39k_12Mar-2025_A100_new

12_bitwise_MQA_llama_model

Llama-3.2-1B-Instruct_sum_DPO_80k_2_1ep

grpo-llama3.2-1b

11_layer_GQA4_llama_model

ours-llama-3.2-1b-mbpp

Llama-2-7b-chat-finetune

Grogros-dm-llama3.2-1BI-OWTWM-OWT-Al4-WT-v10-meta-OWT-LA-ext

6_random_MQA_llama_model

Llama-3.2-1B-Instruct_sum_KTO_1k_1_3ep_4bit

fine_tuned_llama

Grogros-dmWM-llama-3.2-1B-Instruct-WOHealth-Al4-NH-WO-d4-a0.2-v4-WO_NoHealth

Llama-3.2-1B-FC-v1.3-think

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

Grogros-dm-llama3.2-1BI-OWTWM-DWM-Al4-WT-v11-meta-OWT-learnability_adv