Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
aimagelab
/
LLaVA_MORE-llama_3_1-8B-pretrain
like
0
Follow
AImageLab
23
Image-Text-to-Text
Transformers
liuhaotian/LLaVA-CC3M-Pretrain-595K
llava_llama
text-generation
arXiv:
2503.15621
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
refs/pr/1
LLaVA_MORE-llama_3_1-8B-pretrain
42.3 MB
2 contributors
History:
8 commits
nielsr
HF Staff
Add link to paper
aa6b012
verified
8 months ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
README.md
1.33 kB
Add link to paper
8 months ago
config.json
Safe
1.44 kB
Update config.json
over 1 year ago
mm_projector.bin
pickle
Detected Pickle imports (3)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
42 MB
xet
Upload 3 files
over 1 year ago
trainer_state.json
Safe
381 kB
Upload 3 files
over 1 year ago