Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up
openbmb
/
MiniCPM-o-2_6
like
1.27k
Follow
OpenBMB
2.2k
Any-to-Any
Transformers
Safetensors
openbmb/RLAIF-V-Dataset
multilingual
minicpmo
feature-extraction
minicpm-o
omni
vision
ocr
multi-image
video
custom_code
audio
speech
voice cloning
live Streaming
realtime speech conversation
asr
tts
arxiv:
2405.17220
arxiv:
2408.01800
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
55
Deploy
Use this model
7a26a08
MiniCPM-o-2_6
17.4 GB
14 contributors
History:
56 commits
bokesyo
Update system prompt of assistant mode to make sure AudioEvals metric is replicable
7a26a08
verified
10 months ago
assets
add usage samples to readme
10 months ago
.gitattributes
Safe
1.74 kB
add omni case for inference
10 months ago
README.md
Safe
49 kB
Update README.md
10 months ago
added_tokens.json
Safe
1.41 kB
init
11 months ago
config.json
Safe
3.44 kB
init
11 months ago
configuration_minicpm.py
Safe
7.55 kB
update
11 months ago
image_processing_minicpmv.py
Safe
16.7 kB
init
11 months ago
merges.txt
Safe
1.67 MB
init
11 months ago
model-00001-of-00004.safetensors
Safe
4.88 GB
xet
add ckpt
11 months ago
model-00002-of-00004.safetensors
Safe
4.93 GB
xet
add ckpt
11 months ago
model-00003-of-00004.safetensors
Safe
4.33 GB
xet
add ckpt
11 months ago
model-00004-of-00004.safetensors
Safe
3.21 GB
xet
add ckpt
11 months ago
model.safetensors.index.json
Safe
133 kB
add ckpt
11 months ago
modeling_minicpmo.py
Safe
140 kB
Update system prompt of assistant mode to make sure AudioEvals metric is replicable
10 months ago
modeling_navit_siglip.py
Safe
42.1 kB
update
11 months ago
preprocessor_config.json
Safe
714 Bytes
init
11 months ago
processing_minicpmo.py
Safe
20 kB
Release `get_audio_placeholder` interface in processing (#24)
10 months ago
resampler.py
Safe
35.6 kB
init
11 months ago
special_tokens_map.json
Safe
5.35 kB
init
11 months ago
tokenization_minicpmo_fast.py
Safe
3.04 kB
init
11 months ago
tokenizer.json
Safe
7.04 MB
init
11 months ago
tokenizer_config.json
Safe
14.1 kB
init
11 months ago
utils.py
Safe
7.24 kB
update
11 months ago
vocab.json
Safe
2.78 MB
init
11 months ago