Models

Llama-3.2-1B-text

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10k_1_2ep_4bit

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_32_64_0.05_16CLINICALe3c-sentences_tag

beeyeah-reg-0.1-0.00001-0.1

pos_tofu_Llama-3.2-1B-Instruct_retain90_forget10_bio_lr2e-05_wd0.01_epoch10

Llama-3.2-1B-Instruct-RL-gsm8k-step1

Finetuned

RS_1B_RM_iter1

Llama-3.2-1B-Instruct-terapeutico

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

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_16_64_0.01_16CLINICALe3c-sentences_tag

beeyeah-clip-0.1-0.00001-0.2

Llama-3.2-1B-Instruct_sum_PPO_Skywork_177k_2_1ep

Llama-3.2-1B-Instruct_sum_PPO_Skywork_50.0k_2_1ep

Llama-3.2-1B-Instruct_finetuned_1_default

beeyeah-dpo-0.1-0.00001

Llama-3.2-1B-Instruct_sum_KTO_10k_1_1ep_4bit

ErselFit_Finetuned_Llama_1B_V2

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_32_0.01_16CLINICALe3c-sentences_tag

llamapretrained1

Llama-3.2-1B-Instruct_sum_DPO_20k_2_1ep

custom-Llama-2-1b

Llama-3.2-1B-Instruct_sum_KTO_40k_2_1ep

llama3_1B_hh_reject_4

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_16_32_0.01_16CLINICALe3c-sentences_tag

0c2649cc-2fe7-4e88-b672-6da1fee4001f

Llama-3.2-1B_ClinicalWhole_5e-05_constant_512_flattening

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr2e-05_layer5_scoeff10_epoch5

Llama-3.2-1B-Instruct_sum_KTO_10k_1_3ep_4bit

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_16_32_0.01_16CLINICALe3c-sentences_tag

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr2e-05_beta0.1_alpha5_epoch5

llama3.2-3b-sft-full

llama3.2-3b-dpo-finegrained

hug1

one5

Llama-3.2-1B-Instruct-cardio-semi-synth-annotation_r1_O1_f1_LT_zcr_bf16

devspeedllm-ft-v0.0.6

Cardano_plutus

Llama_3_2_1B_Filler_v8_SFT

SmolLM3-DPO-Second-Round

finemath-ablation-infiwebmath-4plus