·
AI & ML interests
None yet
Organizations
vwxyzjn/online_dpo_debug3
Text Generation
• 0.4B • Updated • 19
vwxyzjn/online_dpo_debug2
Updated
Text Generation
• 70.4M • Updated • 25
Text Classification
• 0.9B • Updated • 10
Text Generation
• 0.2B • Updated • 20
Text Classification
• 0.1B • Updated • 9
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_2
Text Generation
• 7B • Updated • 12
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_1
Text Generation
• 7B • Updated • 11
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_4
Text Generation
• 7B • Updated • 11
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.02_num_mini_batches_4
Text Generation
• 7B • Updated • 12
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03_num_mini_batches_1
Text Generation
• 7B • Updated • 10
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.02_num_mini_batches_2
Text Generation
• 7B • Updated • 12
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03_num_mini_batches_4
Text Generation
• 7B • Updated • 10
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03_num_mini_batches_2
Text Generation
• 7B • Updated • 11
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1
Text Generation
• 7B • Updated • 10
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.02_num_mini_batches_4
Text Generation
• 7B • Updated • 11
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.02_num_mini_batches_1
Text Generation
• 7B • Updated • 12
vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_2
Text Generation
• 7B • Updated • 11
Text Generation
• 1B • Updated • 40
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.03
Text Generation
• 7B • Updated • 10
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.05
Text Generation
• 7B • Updated • 11
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.15
Text Generation
• 7B • Updated • 12
vwxyzjn/ppo_zephyr_vllm_1e-6_kl_0.20
Text Generation
• 7B • Updated • 10
Text Generation
• 7B • Updated • 16
Text Generation
• 7B • Updated • 15
Text Classification
• 7B • Updated • 7