Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
thrunlab
/
Mistral_Sparse_refined_web_50p_graceful_False
like
0
Text Generation
Transformers
Safetensors
sparse_mistral
Generated from Trainer
custom_code
Model card
Files
Files and versions
Community
Train
Use this model
main
Mistral_Sparse_refined_web_50p_graceful_False
1 contributor
History:
4 commits
lukeleeai
Training in progress, step 500
9df91cd
verified
5 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
README.md
1.25 kB
End of training
5 months ago
config.json
915 Bytes
Training in progress, step 250
5 months ago
generation_config.json
111 Bytes
End of training
5 months ago
model.safetensors
16.6 MB
LFS
Training in progress, step 500
5 months ago
sparsification_sftt.py
33.5 kB
End of training
5 months ago
special_tokens_map.json
437 Bytes
End of training
5 months ago
tokenizer.json
1.8 MB
End of training
5 months ago
tokenizer_config.json
969 Bytes
End of training
5 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.training_args.TrainingArguments"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
How to fix it?
4.73 kB
LFS
Training in progress, step 250
5 months ago