Models

TinyLlama-3.2-1B-LoRA-Finetuned-2

customer-success-assistant

Llama-3.2-1B-Instruct-EL-SynthDolly-1A-E1

llama3.2-alpaca-tuned-and-merged

llama-3.2-3b-sft-llama-star

g-llama-3b-finetuned

llama-1b-cov-matched-l2-lam100

llamasrnn-grpo-epoch001-merged

ORPO8000Vikhr-Llama-3.2-1B-Instruct5000

magictokens_finetune_merged

tofu_Llama-3.2-3B-Instruct_forget01_NPO_beta1.0_lr1e-5

llama3_2_3b_instruct_only_rsn_tuned_lr5e-5

llama3.2-1b-Inst-safegrad

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232

assn2-dpo-llama-1b

assn2-simpo-llama32-1b

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch8_20260429_145817_step232

tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_qat-int4

assn2-dpo

tofu_Llama-3.2-1B-Instruct_forget10_RMU_qat-int4

tofu_1B_f10_GD_lr1e-5_a5.0

llama3.2-1b-Inst-arithmetic

helpfulpharmacyllm_js-rlhf-01

llama3.2_1b_16bit

Llama-3.2-1b-Instruct-smashed

STaR_RL_DAPO

64b_RL_DAPO_v2

DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh

1_to_16_analysis

Llama-3.2-3B-Instruct-MPO-SKD-V2

air-compliance-llama-1b

Llama-3.2-3B-Instruct-attention-layers

Llama-3.2-3B-Instruct-minimal-layers

Llama-3.2-3B-Instruct-layers-16-to-24

test_gin_rummy_qwen_2-5_3B

Llama-3.2-3B-Instruct_slime

train_mrpc_42_1774791061

train_boolq_42_1774791063

FAME-topics_PO_llama32-1b-instruct-qa

FAME-topics_GA_llama32-1b-instruct-qa

FAME-topics_PO_llama32-3b-instruct-qa

llama_3b_instruct_think_sft_nopack_lr1.5e5_ep3