arxiv:2404.00438
Kaizhao Liang
kz919
AI & ML interests
LLM solving real tangible problems
Organizations
models
35
kz919/Mistral-7B-orca-dpo-8h
Text Generation
•
Updated
•
5
kz919/Mistral-7B-orca-dpo-12h
Text Generation
•
Updated
•
6
kz919/mistral-7b-clf-router-reward-sft-mistral-7b
Text Classification
•
Updated
•
1
kz919/mistral-7b-clf-router-reward-e5-mistral-7b-instruct
Text Classification
•
Updated
•
2
•
2
kz919/mistral-7b-clf-router-reward-pretrained-mistral-7b-open-orca
Text Classification
•
Updated
•
2
•
1
kz919/mistral-7b-dpo-open-orca-flan-50k-synthetic-5-models
Text Generation
•
Updated
•
2.92k
•
1
kz919/mistral-7b-sft-open-orca-flan-50k
Text Generation
•
Updated
•
2.92k
•
1
kz919/mistral-7b-clf-open-orca-flan-50k-synthetic-5-models
Text Classification
•
Updated
•
2
•
1
kz919/ntk_scaled_open_llama_13b_32k
Text Generation
•
Updated
•
7
•
5
kz919/ntk_scaled_open_llama_13b_16k
Text Generation
•
Updated
•
6
datasets
19
kz919/coe_router_golden_reference_with_completion_teacher_forcing_loss
Viewer
•
Updated
•
2
•
1
kz919/coe_router_golden_reference_with_completion
Viewer
•
Updated
•
60
•
1
kz919/open-orca-flan-200k-teacher-forcing-loss
Viewer
•
Updated
•
1
kz919/mmlu-auxiliary-train-e5-mistral-7b-instruct
Viewer
•
Updated
•
1
kz919/coe_router_golden_reference
Viewer
•
Updated
•
2
•
1
kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct-v8
Viewer
•
Updated
kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct-v7
Viewer
•
Updated
•
2
kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct-v6
Viewer
•
Updated
•
1
kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct-v5
Viewer
•
Updated
kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct-v4
Viewer
•
Updated
•
1