Models

gpt-semi-wtype-Llama-tuned-Lora-merged-gpt5

Llama3.2-3B-DELLA-Math-Code

polyalign-llama3.2-3b-en-sft

Llama3.2-3B-DareTIES-Math-Code

Llama3.2-3B-Dare-Math-Code

cloud-agent

Llama3.2-3B-BreadcrumbsTIES-Math-Code

Llama3.2-3B-TIES-Math-Code

Llama3.2-3B-Arcee-Code-Math

Llama3.2-3B-SLERP-Math-Code

AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-text-retriever-grpo-repetition-penalty

Latent-SFT-Llama3.2-Instruct-1B-COT-SFT

Llama-3.2-3B-Instruct-GRPO-merged

Minmax-TOFU-2

qp-3.2-1B

dagbani-llama32-lora-finetuned

Llama-3.2-3B-Instruct-hhrlhf

assn2-simpo-llama-1b

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch8_20260429_145921_step232

hw2-dpo

tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-int4

llama32-3b-medical-sft-drift

tofu_1B_f10_GD_lr1e-5_a1.0

tofu_1B_f10_RMU_lr1e-5_sc10

fdcbbcdf

Llama-3.2-1B-Instruct-commonsense_qa-MGSM8K-sft1-slerp

engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3

c717bb90-3c4c-4fab-947c-310e4cec2d00

Llama3-weeslee-Ko-3.2-3B

llama1b-sft

helpfulpharmacyllm_mb-rlhf-01

Llama-3.2-1B-SFT

BaseModel-rlhf-01

DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh

Llama-3.2-3B-Instruct-mlp-layers

liarsdice-smoketest-hashid

train_cola_42_1774791067

train_rte_42_1774791065

llama_3b_instruct_non_think_sft_nopack_lr1.5e5_ep3

Llama-3.2-3B-Instruct-C_M_T-DOLLY

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM

llama3.2-1b-deita-dpo-student_sft_init