CoPE is a drop-in enhancement of RoPE that delivers consistent gains within the training context and during long-context extrapoaltion.
Haoran Li PRO
haoranli-ml
·
AI & ML interests
ML, RL, Foundation Models
Recent Activity
updated
a dataset about 18 hours ago
haoranli-ml/genvf_td_data published
a dataset about 18 hours ago
haoranli-ml/genvf_td_data published
a dataset 4 days ago
haoranli-ml/GVF-3k Organizations
models 29
haoranli-ml/Llama-3-8B-HardClip-64k-Instruct
8B • Updated
• 21
haoranli-ml/Llama-3-8B-HardClip-64k-Base
8B • Updated
• 28
haoranli-ml/Llama-3-8B-RoPE-64k-Base
8B • Updated
• 19
haoranli-ml/Llama-3-8B-CoPE-64k-Base
8B • Updated
• 20
haoranli-ml/Llama-3-8B-CoPE-64k-Instruct
Text Generation • 8B • Updated
• 32
haoranli-ml/Llama-3-8B-RoPE-64k-Instruct
Text Generation • 8B • Updated
• 30
haoranli-ml/VF_future_prompts_hl_gauss_corrected_cdf_bin_012sigma_future_condition_1_18
Updated
haoranli-ml/VF_old_prompt_hl_gauss_corrected_cdf_bin_012sigma_reverse_kl_no_entropy
Updated
haoranli-ml/VF_future_prompts_hl_gauss_corrected_cdf_bin_012sigma_future_condition
Updated
haoranli-ml/VF_future_prompts_hl_gauss_corrected_cdf_bin_012sigma
Updated
datasets 96
haoranli-ml/genvf_td_data
Viewer
• Updated
• 13.6k • 2
haoranli-ml/GVF-3k
Viewer
• Updated
• 3k • 22
haoranli-ml/genvf-v3-difficulty
Viewer
• Updated
• 13.8k • 19
haoranli-ml/genvf-v3-train-holdout-60-both_prefix
Viewer
• Updated
• 60 • 59
haoranli-ml/genvf-v3-train-holdout-60-with_branch_rewards
Viewer
• Updated
• 60 • 13
haoranli-ml/hold_out_60
Viewer
• Updated
• 60 • 13
haoranli-ml/APEX-Int
Viewer
• Updated
• 49 • 19
haoranli-ml/AMO-Bench-Int
Viewer
• Updated
• 30 • 33
haoranli-ml/VF_gemini_summaries_final
Viewer
• Updated
• 6.89k • 28
haoranli-ml/VF_gemini_summaries_train_sanity_check_v2
Viewer
• Updated
• 10 • 16