Models

llama2_7b_only_sn_tuned_lr3e-5

akeno-v7-epoch2-merged

triage_mistral_finetuned

Co-rewarding-II-Qwen3-8B-Base-DAPO14k

llama3.1_8b_base_gsm8k_ft_freeze_sn_lr3e-5

qwen3-vl-8b-ac-2-base-stage2-lora-epoch1

llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5

llama31-8b-gdpo-v7-step50

qwen-coder-7b-sap-harmful-code

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5

exam-mcq-model

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-margin-qa-only-0.02-kl-4e-6-reward-2_step_33

Llama-3.1-8B_reasoning

llama2_7b_chat_resta_lr5e-5_y0.5

Llama-3.1-8B_instruction

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch1

benchmark-luckypick-7b-19

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch2

qwen3-vl-8b-mmrl-grpo-step100

Qwen2.5-Coder-RETAIN-MCEVALHARD-7B-Base

qwen3-vl-8b-invoice-cpt