Models

OrpoLlama-3.2-1B-V1_q4_k_m

rationale_model_e3_save5000_f4

medical_helper_pedqa

Experiment46

finetuning-model-16bit

Experiment42

Llama-3.2-1B-Instruct_SFT_wait

Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix2

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_16_32_0.05_16CLINICALe3c-sentences_tag

matchup_llama3_1b_merge

Llama3.2_1B-Instruct

LocoLamav3M4bit

lora_model_r16_merged16

llama32_1bi_CoTsft_rs0_3_5cut_all2_e2

Experiment5

Experiment22

sallumallu-llama-3.2.Instruct

Llama-3.2-1B_AllDataSources_8e-06_constant_512

odinbot-finetuned-v2-10022024

rationale_model_e3_save5000_f3

Experiment13

Hyperparameter14

Llama-3.2-1B-Instruct-activation-SecretSauce2-5.0-AlpacaPoison-long2

hero-bcc

banking_helper

twentyK_SocraticCaML_Llama1bUnsloth

llama-3.2-1681

LLama3-1B-OWM-DKD-5

Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaRefuseSmooth-lowlr1

Llama-3.2-1B-Instruct_finetuned_s04_i

llama32_1b_scoring_selfexplanation

potato_wizard_v38

llama-31b_question

Llama-3.2-1B-Instruct_finetuned_s01

Hyperparameter1

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

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaRefuse-sauce2

llama3.2-1b-Open-R1-GRPO-test0

llama-3.2-1B-instruct-sft

llama1Bredmerged-FinetunedByAG

model

Llama-3.2-1B-Instruct-distillation-AlpacaGPT4-BadCode-s2