Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DandinPower
/
taide_7b_lora_completion_only
like
0
PEFT
Safetensors
DandinPower/ZH-Reading-Comprehension-TAIDE-Chat
Chinese
trl
sft
nycu-112-2-deeplearning-hw2
Generated from Trainer
License:
other
Model card
Files
Files and versions
Community
Use this model
6a9e072
taide_7b_lora_completion_only
1 contributor
History:
9 commits
DandinPower
Training in progress, step 2000
6a9e072
verified
4 months ago
.gitattributes
1.52 kB
initial commit
4 months ago
adapter_config.json
648 Bytes
Training in progress, step 250
4 months ago
adapter_model.safetensors
67.1 MB
LFS
Training in progress, step 2000
4 months ago
special_tokens_map.json
548 Bytes
Training in progress, step 250
4 months ago
tokenizer.json
2.48 MB
Training in progress, step 250
4 months ago
tokenizer.model
813 kB
LFS
Training in progress, step 250
4 months ago
tokenizer_config.json
2.04 kB
Training in progress, step 250
4 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"__main__.MyTrainingArguments"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"torch.float32"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.state.PartialState"
How to fix it?
6.39 kB
LFS
Training in progress, step 250
4 months ago