Pre-trained models in MiniPLM: Knowledge Distillation for Pre-Training Language Models

MiniLLM
community
AI & ML interests
Training efficient language models (MiniLLM, MiniPLM)
Organization Card
Collections
2
models
50

MiniLLM/init-gpt2-120M
Text Generation
•
Updated
•
69
•
1

MiniLLM/teacher-Llama-13B
Text Generation
•
Updated
•
21

MiniLLM/MiniLLM-Llama-7B
Text Generation
•
Updated
•
42
•
1

MiniLLM/Ref-Pretrain-Qwen-104M
Text Generation
•
Updated
•
1.5k
•
2

MiniLLM/MiniPLM-Mamba-130M
Text Generation
•
Updated
•
32
•
2

MiniLLM/MiniPLM-Qwen-1.2B
Text Generation
•
Updated
•
52
•
2

MiniLLM/MiniPLM-Qwen-500M
Text Generation
•
Updated
•
112
•
5

MiniLLM/MiniPLM-Qwen-200M
Text Generation
•
Updated
•
176
•
2

MiniLLM/MiniPLM-llama3.1-212M
Text Generation
•
Updated
•
279
•
•
3

MiniLLM/Pretrain-Qwen-500M
Text Generation
•
Updated
•
57
datasets
10
MiniLLM/pile-tokenized
Updated
•
35
•
1
MiniLLM/roberta-corpus-processed
Updated
•
68
MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5
Updated
•
136
MiniLLM/openwebtext-processed
Updated
•
80
MiniLLM/dolly-processed
Viewer
•
Updated
•
110k
•
215
•
1
MiniLLM/sinst
Viewer
•
Updated
•
8.35k
•
149
•
1
MiniLLM/uinst
Viewer
•
Updated
•
64.8k
•
210
•
1
MiniLLM/self-inst
Viewer
•
Updated
•
242
•
104
•
2
MiniLLM/Vicuna
Viewer
•
Updated
•
80
•
121
•
1
MiniLLM/dolly
Viewer
•
Updated
•
500
•
232