Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Fsoft-AIC
/
Phi3-CLIP-MoE
like
0
Follow
FPT Software AI Center
60
Image-Text-to-Text
Safetensors
English
arxiv:
2411.00918
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
14
refs/pr/8
Phi3-CLIP-MoE
/
sft
/
smoe
9.59 GB
1 contributor
History:
3 commits
DavidNguyen
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
aba7374
verified
11 months ago
added_tokens.json
Safe
293 Bytes
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
config.json
Safe
1.81 kB
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
generation_config.json
Safe
193 Bytes
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
latest
Safe
15 Bytes
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
model-00001-of-00002.safetensors
Safe
4.97 GB
xet
5fd301f859a9f8273190fca1f607f3e43e6116b4636f8c793e156b9b0874e1db
11 months ago
model-00002-of-00002.safetensors
Safe
4.61 GB
xet
b896fb3978c2bbce43d348214ec534e3a1b6bbb733729bd2956ffb44863537b0
11 months ago
model.safetensors.index.json
Safe
101 kB
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
rng_state_0.pth
pickle
Detected Pickle imports (7)
"numpy.dtype"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"numpy.core.multiarray._reconstruct"
How to fix it?
15 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
rng_state_1.pth
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
15 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
rng_state_2.pth
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
15 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
rng_state_3.pth
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
15 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
special_tokens_map.json
Safe
447 Bytes
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
tokenizer.model
Safe
500 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
tokenizer_config.json
Safe
3.23 kB
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
trainer_state.json
Safe
2.06 MB
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
training_args.bin
pickle
Detected Pickle imports (13)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"moe_model.train.train.TrainingArguments"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.bfloat16"
How to fix it?
8.12 kB
xet
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago
zero_to_fp32.py
Safe
25.3 kB
b41c4636d2fc8dff4c242d49588ee4640d4c2714a399cf69978c574047451e4f
11 months ago