·
AI & ML interests
None yet
Organizations
None yet
jasonhuang3/Pro6000-caldpo-dataset-our-13-2-llama3-8b-instruct-merged
8B • Updated • 1
jasonhuang3/Pro6000-caldpo-dataset-our-13-2-llama3-8b-instruct-lora
Updated
jasonhuang3/207-caldpo-dataset-our-13-2-llama3-1-8b-instruct-merged
jasonhuang3/Pro6000-caldpo-dataset-our-40-qwen-2-5-7b-math-merged
jasonhuang3/207-caldpo-dataset-our-13-2-llama3-1-8b-instruct-lora
Updated
jasonhuang3/Pro6000-caldpo-dataset-our-40-qwen-2-5-7b-math-lora
Updated
jasonhuang3/Pro6000-caldpo-dataset-our-13-qwen-2-5-7b-math-merged
jasonhuang3/Pro6000-caldpo-dataset-our-13-qwen-2-5-7b-math-lora
Updated
jasonhuang3/Pro6000-caldpo-dataset-qwen-2-5-7b-math-bpo-merged
jasonhuang3/Pro6000-caldpo-dataset-qwen-2-5-7b-math-bpo-lora
Updated
jasonhuang3/207-caldpo-dataset-dpo-qwen-2-5-7b-math-merged
8B • Updated jasonhuang3/207-caldpo-dataset-dpo-qwen-2-5-7b-math-lora
Updated
jasonhuang3/Pro6000-caldpo-dataset-our-13-2-qwen-2-5-7b-math-merged
8B • Updated jasonhuang3/Pro6000-caldpo-dataset-our-13-2-qwen-2-5-7b-math-lora
Updated
jasonhuang3/207-our-13-2-qwen-2-5-math-1-5b-instruct-merged-28k
2B • Updated jasonhuang3/207-our-13-2-qwen-2-5-math-7b-instruct-merged-28k
8B • Updated jasonhuang3/Pro6000-llama3-2-3b-instruct-our-13-2-merged-28k
3B • Updated jasonhuang3/Pro6000-llama3-8b-instruct-our-13-2-merged-28k
8B • Updated jasonhuang3/Pro6000-llama3-2-3b-instruct-our-13-2-lora-28k
Updated
jasonhuang3/207-our-13-2-qwen-2-5-math-1-5b-instruct-lora-28k
Updated
jasonhuang3/Pro6000-llama3-8b-instruct-our-13-2-lora-28k
Updated
jasonhuang3/207-our-13-2-qwen-2-5-math-7b-instruct-lora-28k
Updated
jasonhuang3/Pro6000-llama3-1-8b-instruct-our-13-2-merged-28k
8B • Updated jasonhuang3/Pro6000-llama3-1-8b-instruct-our-13-2-lora-28k
Updated
jasonhuang3/Pro6000-our-53-qwen-2-5-7b-math-merged-28k
8B • Updated jasonhuang3/Pro6000-our-53-qwen-2-5-7b-math-lora-28k
Updated
jasonhuang3/taitung-sft-2187-1107-merged
8B • Updated • 1
jasonhuang3/Pro6000-our-52-qwen-2-5-7b-math-merged-28k
8B • Updated jasonhuang3/Pro6000-our-52-qwen-2-5-7b-math-lora-28k
Updated
jasonhuang3/Pro6000-our-51-qwen-2-5-7b-math-merged-28k
8B • Updated