AI/MiniCPM-o-2_6-int4

Fork 0

mirror of https://www.modelscope.cn/OpenBMB/MiniCPM-o-2_6-int4.git synced 2025-08-20 06:39:06 +08:00

Go to file

Hongji Zhu 47d04c823c update

2025-01-15 19:54:09 +08:00

.gitattributes

System init .gitattributes

2025-01-13 10:14:14 +00:00

added_tokens.json

init

2025-01-15 17:27:21 +08:00

config.json

init

2025-01-15 17:27:21 +08:00

configuration_minicpm.py

init

2025-01-15 17:27:21 +08:00

configuration.json

System init configuration.json

2025-01-13 10:14:15 +00:00

gitattributes

init

2025-01-15 17:27:21 +08:00

image_processing_minicpmv.py

init

2025-01-15 17:27:21 +08:00

merges.txt

init

2025-01-15 17:27:21 +08:00

model.safetensors

init

2025-01-15 17:27:21 +08:00

modeling_minicpmo.py

update

2025-01-15 19:54:09 +08:00

modeling_navit_siglip.py

init

2025-01-15 17:27:21 +08:00

preprocessor_config.json

init

2025-01-15 17:27:21 +08:00

processing_minicpmo.py

init

2025-01-15 17:27:21 +08:00

quantize_config.json

init

2025-01-15 17:27:21 +08:00

README.md

update

2025-01-15 19:54:09 +08:00

resampler.py

init

2025-01-15 17:27:21 +08:00

special_tokens_map.json

init

2025-01-15 17:27:21 +08:00

tokenization_minicpmo_fast.py

init

2025-01-15 17:27:21 +08:00

tokenizer_config.json

init

2025-01-15 17:27:21 +08:00

tokenizer.json

init

2025-01-15 17:27:21 +08:00

utils.py

init

2025-01-15 17:27:21 +08:00

vocab.json

init

2025-01-15 17:27:21 +08:00

README.md

pipeline_tag

datasets

library_name

language

A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

MiniCPM-o 2.6 int4

This is the int4 quantized version of MiniCPM-o 2.6.
Running with int4 version would use lower GPU memory (about 9GB).