Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Fsoft-AIC
/
Phi3.5-Siglip-MoE
like
0
Follow
FPT Software AI Center
39
Image-Text-to-Text
Safetensors
English
arxiv:
2411.00918
License:
apache-2.0
Model card
Files
Files and versions
Community
6
main
Phi3.5-Siglip-MoE
/
sft
/
smoe_cosinegating
1 contributor
History:
1 commit
DavidNguyen
Upload folder using huggingface_hub (
#5
)
b0d4dde
verified
4 days ago
added_tokens.json
293 Bytes
Upload folder using huggingface_hub (#5)
4 days ago
config.json
4.28 kB
Upload folder using huggingface_hub (#5)
4 days ago
generation_config.json
193 Bytes
Upload folder using huggingface_hub (#5)
4 days ago
model-00001-of-00003.safetensors
4.97 GB
LFS
Upload folder using huggingface_hub (#5)
4 days ago
model-00002-of-00003.safetensors
4.99 GB
LFS
Upload folder using huggingface_hub (#5)
4 days ago
model-00003-of-00003.safetensors
249 MB
LFS
Upload folder using huggingface_hub (#5)
4 days ago
model.safetensors.index.json
114 kB
Upload folder using huggingface_hub (#5)
4 days ago
special_tokens_map.json
447 Bytes
Upload folder using huggingface_hub (#5)
4 days ago
tokenizer.model
500 kB
LFS
Upload folder using huggingface_hub (#5)
4 days ago
tokenizer_config.json
3.4 kB
Upload folder using huggingface_hub (#5)
4 days ago
trainer_state.json
1.45 MB
Upload folder using huggingface_hub (#5)
4 days ago
training_args.bin
pickle
Detected Pickle imports (13)
"torch.device"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"torch.bfloat16"
,
"transformers.trainer_utils.SchedulerType"
,
"moe_model.train.train.TrainingArguments"
How to fix it?
8.18 kB
LFS
Upload folder using huggingface_hub (#5)
4 days ago