ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000
Text Generation • 7B • Updated
• 84
ewqrweqkmk
ewqr2130
AI & ML interests
None yet
Organizations
None yet
models 21
ewqr2130/llama_sft_longer
Text Generation • 7B • Updated
• 76
ewqr2130/llama_ppo_1e6step_4000
Text Generation • 7B • Updated
• 80
ewqr2130/llama2-sft-16000
Text Generation • 7B • Updated
• 1
ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
Text Generation • 7B • Updated
• 664
ewqr2130/phi_ppo_phi_RM_1e6step_9500
Text Generation • 3B • Updated
• 1
ewqr2130/mistral-7b-sft-beta__100000_1e-05_RewardModel_2GPU
Text Classification • 7B • Updated
• 3
ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
Text Generation • 7B • Updated
• 653
ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102
Text Generation • 7B • Updated
• 657
ewqr2130/phi_ppo_1e-5_REAL_1GPU_batch8step_2400
Text Generation • 3B • Updated