jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.85-4xh200-batch-64-20260421-233802
Text Generation • 8B • Updated • 4 •
jackfeng
jackf857
AI & ML interests
None yet
Recent Activity
updated a model 23 days ago
jackf857/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.2 updated a dataset 23 days ago
jackf857/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.2-margin published a dataset 23 days ago
jackf857/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.2-marginOrganizations
jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.6-4xh200-batch-64-20260421-214335-rerun
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-new-dpo-harmless-4xh200-s_star1.0
Text Generation • 8B • Updated • 4 •
jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
Text Generation • 8B • Updated • 421 •
jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64
Text Generation • 8B • Updated • 41 •
jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64
Text Generation • 8B • Updated • 4 •
jackf857/qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64
Text Generation • 8B • Updated • 5 •
jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-r-dpo-ultrafeedback-4xh200
Text Generation • 8B • Updated • 60 •
jackf857/llama-3-8b-base-margin-dpo-hh-helpful-batch-64
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-margin-dpo-hh-harmless-batch-size-64
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-orpo-ultrafeedback-keep-start-beta-0p5
Updated
jackf857/llama-3-8b-base-simpo-8xh200
Text Generation • 8B • Updated • 65 •
jackf857/llama-3-8b-base-slic-hf-ultrafeedback-4xh200
Text Generation • 8B • Updated • 5 •
jackf857/llama-3-8b-base-orpo-ultrafeedback-8xh200
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-kto-ultrafeedback-8xh200
Text Generation • 8B • Updated • 4 •
jackf857/llama-3-8b-base-cpo-ultrafeedback-8xh200
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-robust-dpo-ultrafeedback-8xh200
Text Generation • 8B • Updated • 4 •
jackf857/llama-3-8b-base-ipo-ultrafeedback-8xh200
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-margin-dpo-hh-4xh100
Text Generation • 8B • Updated • 3 •
jackf857/llama-3-8b-base-margin-dpo-4xh100-pilot
Updated
jackf857/llama-3-8b-base-margin-dpo-4xh100
Text Generation • 8B • Updated • 8 •
jackf857/llama3-8b-hh-helpful-margin-dpo
2B • Updated • 1
jackf857/llama3-helpful-base-hh-correct-2-edpo
8B • Updated • 4
jackf857/llama3-helpful-base-hh-correct-1-edpo
8B • Updated
jackf857/llama3-helpful-base-hh-edpo
8B • Updated • 11
jackf857/llama3-harmless-base-hh-edpo
8B • Updated • 2
jackf857/llama3-e-dpo-hh-helpful-base
8B • Updated • 1
jackf857/Llama3-8b-ultrafeedback-binarized-e-dpo
Text Generation • 8B • Updated