ewqrweqkmk

ewqr2130 's models 21

Sort:  Recently updated

ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000

Text Generation • 7B • Updated Feb 4, 2024 • 90

ewqr2130/llama_sft_longer

Text Generation • 7B • Updated Jan 31, 2024 • 93

ewqr2130/llama_ppo_1e6step_4000

Text Generation • 7B • Updated Jan 31, 2024 • 88

ewqr2130/llama2-sft-16000

Text Generation • 7B • Updated Jan 27, 2024 • 4

ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000

Text Generation • 7B • Updated Jan 22, 2024 • 207

ewqr2130/phi_ppo_phi_RM_1e6step_9500

Text Generation • 3B • Updated Jan 22, 2024 • 7

ewqr2130/mistral-7b-sft-beta__100000_1e-05_RewardModel_2GPU

Text Classification • 7B • Updated Jan 19, 2024 • 9

ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2

Text Generation • 7B • Updated Jan 19, 2024 • 210

ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102

Text Generation • 7B • Updated Jan 19, 2024 • 202

ewqr2130/phi_ppo_1e-5_REAL_1GPU_batch8step_2400

Text Generation • 3B • Updated Jan 19, 2024 • 4

ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51

Text Generation • 7B • Updated Jan 19, 2024 • 212

ewqr2130/alignment-handbook-zephyr-7b_ppostep_100

Text Generation • 7B • Updated Jan 18, 2024 • 202

ewqr2130/TinyLamma-DPO-40k-Steps

Updated Jan 16, 2024

ewqr2130/phi2_sft

Text Generation • 3B • Updated Jan 15, 2024 • 6

ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1

Text Generation • 7B • Updated Jan 15, 2024 • 209

ewqr2130/TinyLamma-SFT

Text Generation • 1B • Updated Jan 14, 2024 • 217 •

ewqr2130/moe_scratch

Text Generation • 47B • Updated Jan 8, 2024 • 4

ewqr2130/llama2-7b-raw-sft

Text Generation • 7B • Updated Jan 8, 2024 • 227

ewqr2130/mistral-inst-v02-dpo

Text Generation • 7B • Updated Jan 8, 2024 • 219

ewqr2130/mistral-7b-raw-sft

Text Generation • 7B • Updated Jan 8, 2024 • 227

ewqr2130/your-model-name

Text Classification • 1B • Updated Jan 1, 2024 • 6