Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Fsoft-AIC
/
Phi3.5-Siglip-MoE
like
0
Follow
FPT Software AI Center
64
Image-Text-to-Text
TensorBoard
Safetensors
English
arxiv:
2411.00918
License:
apache-2.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
6187
refs/pr/6180
Phi3.5-Siglip-MoE
/
CompeteSMoE
/
competesmoe_versions
/
Full_CS_BS_theta0.2_RL0.01_softmax_competesmoev30
10.2 GB
1 contributor
History:
1 commit
DavidNguyen
Upload folder using huggingface_hub
bedbad8
verified
5 months ago
added_tokens.json
Safe
293 Bytes
Upload folder using huggingface_hub
5 months ago
config.json
5.25 kB
Upload folder using huggingface_hub
5 months ago
generation_config.json
Safe
193 Bytes
Upload folder using huggingface_hub
5 months ago
model-00001-of-00003.safetensors
4.97 GB
xet
Upload folder using huggingface_hub
5 months ago
model-00002-of-00003.safetensors
4.99 GB
xet
Upload folder using huggingface_hub
5 months ago
model-00003-of-00003.safetensors
249 MB
xet
Upload folder using huggingface_hub
5 months ago
model.safetensors.index.json
114 kB
Upload folder using huggingface_hub
5 months ago
special_tokens_map.json
Safe
447 Bytes
Upload folder using huggingface_hub
5 months ago
tokenizer.model
Safe
500 kB
xet
Upload folder using huggingface_hub
5 months ago
tokenizer_config.json
Safe
3.4 kB
Upload folder using huggingface_hub
5 months ago
trainer_state.json
11.4 MB
xet
Upload folder using huggingface_hub
5 months ago
training_args.bin
pickle
Detected Pickle imports (13)
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"accelerate.state.PartialState"
,
"moe_model.train.train.TrainingArguments"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.bfloat16"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
How to fix it?
7.99 kB
xet
Upload folder using huggingface_hub
5 months ago