·
AI & ML interests
None yet
Organizations
None yet
gohsyi/Meta-Llama-3.1-8B-Instruct-ppo4-ultrafeedback-v0.1-ckpt-step10
Text Generation
• 8B • Updated gohsyi/Meta-Llama-3-8B-Instruct-em
8B • Updated gohsyi/Llama-3.1-8B-Instruct-em
8B • Updated 9B • Updated gohsyi/Llama-3.1-8B-sft-metamath
gohsyi/Llama-3.2-3B-sft-metamath
gohsyi/Llama-3.2-1B-sft-metamath
Text Generation
• 3B • Updated Text Generation
• 1B • Updated • 3
• Text Generation
• 8B • Updated gohsyi/Llama-3.2-3B-Instruct-rm-ultrafeedback
gohsyi/Llama-3.2-1B-Instruct-rm-ultrafeedback
gohsyi/Meta-Llama-3.1-8B-sft-ultrafeedback-v0.1
8B • Updated gohsyi/Meta-Llama-3.1-8B-Instruct-raft4-ultrafeedback
Updated
gohsyi/Meta-Llama-3.1-8B-Instruct-sft-ultrafeedback-v0.1
8B • Updated gohsyi/gemma-2-2b-ppo-ultrafeedback-v0.1
3B • Updated gohsyi/gemma-2-2b-it-ppo-ultrafeedback-v0.1
Updated
gohsyi/gemma-2-2b-it-ppo4-ultrafeedback-v0.1
3B • Updated gohsyi/Meta-Llama-3.1-8B-Instruct-ppo4-ultrafeedback-v0.1
8B • Updated gohsyi/gemma-2-2b-it-ppo4-rwt-ultrafeedback-v0.1
3B • Updated • 4
gohsyi/Meta-Llama-3.1-8B-ppo-ultrafeedback-v0.1
8B • Updated gohsyi/Meta-Llama-3.1-8B-Instruct-ppo-ultrafeedback-v0.1
8B • Updated gohsyi/Meta-Llama-3.1-8B-Instruct-ppo4-rwt-ultrafeedback-v0.1
8B • Updated gohsyi/gemma-2-2b-raft4-ultrafeedback
3B • Updated gohsyi/Meta-Llama-3.1-8B-ppo4-ultrafeedback-v0.1
8B • Updated gohsyi/Meta-Llama-3.1-8B-dpo-ultrafeedback
Updated
gohsyi/Meta-Llama-3.1-8B-Instruct-dpo-ultrafeedback
8B • Updated gohsyi/Meta-Llama-3.1-8B-sft-metamath
8B • Updated • 3
gohsyi/Llama-3.1-8B-rm-ultrafeedback
8B • Updated gohsyi/Meta-Llama-3.1-8B-sft
8B • Updated • 5
• 1