·
AI & ML interests
None yet
Organizations
None yet
jasonhuang3/Pro6000-ipo-qwen-2-5-7b-math_lora_28k_merged
Text Generation
• 8B • Updated • 1
jasonhuang3/Pro6000-dpop_our_13_9-qwen-2-5-7b-math_merged_28k
8B • Updated • 2
jasonhuang3/Pro6000-dpop_our_13_9-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-dpop_our_13_8-qwen-2-5-7b-math_merged_28k
8B • Updated • 3
jasonhuang3/Pro6000-dpop_our_13_8-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/99-caldpo-dataset-dpop-our-13-2-zephyr-7b-sft-full-lora-28k
Updated
jasonhuang3/99-DPOP-our-13-7-qwen-2-5-7b-math-lora-1003
Updated
jasonhuang3/Pro6000-dpop_our_13_6-qwen-2-5-7b-math_merged_28k
8B • Updated • 3
jasonhuang3/Pro6000-dpop_our_16-qwen-2-5-7b-math_merged_28k
8B • Updated • 2
jasonhuang3/Pro6000-dpop_our_13_6-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-dpop_our_16-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/99-caldpo-dataset-dpop-our-13-5-zephyr-7b-sft-full-merged-28k
7B • Updated • 3
jasonhuang3/99-caldpo-dataset-dpop-our-13-5-zephyr-7b-sft-full-lora-28k
Updated
jasonhuang3/Pro6000-dpop_our_13_5-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-dpop_our_13_5-qwen-2-5-7b-math_merged_28k
8B • Updated • 3
jasonhuang3/99-bpo-qwen-2-5-7b-math-merged-new-prompt-0927
8B • Updated • 2
jasonhuang3/Pro6000-dpop_our_13_4-qwen-2-5-7b-math_merged_28k
8B • Updated • 5
jasonhuang3/Pro6000-dpop_our_13_4-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-caldpo-dataset-dpop-our-13-2-zephyr-7b-sft-full-lora-28k
Updated
jasonhuang3/Pro6000-dpop_our_13_3-qwen-2-5-7b-math_merged_28k
8B • Updated • 3
jasonhuang3/99-bpo-qwen-2-5-7b-math-lora-new-prompt-0927
Updated
jasonhuang3/Pro6000-dpop_our_13_3-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-dpop_our_13_2-qwen-2-5-7b-math_merged_28k
8B • Updated • 4
jasonhuang3/Pro6000-dpop_our_13_2-qwen-2-5-7b-math_lora_28k
Updated
jasonhuang3/Pro6000-llama3-2-1b-instruct-dpo-merged-28k
1B • Updated • 3
jasonhuang3/Pro6000-llama3-2-1b-instruct-dpop-our-13-merged-28k
1B • Updated • 3
jasonhuang3/Pro6000-llama3-2-1b-instruct-dpo-lora-28k
Updated
jasonhuang3/Pro6000-llama3-2-1b-instruct-dpop-our-13-lora-28k
Updated
jasonhuang3/Pro6000-bpo-qwen-2-5-7b-math-balance-hinge-alpha-0.3-lora-28k-0926
Updated
jasonhuang3/Pro6000-llama3-1-8b-instruct-dpop-our-13-merged-28k
8B • Updated • 2