Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mehmetkeremturkcan
/
SmollerLM-20M-Instruct-Pruned-sft5-dpo3
like
0
Text Generation
Transformers
TensorBoard
Safetensors
trl-lib/ultrafeedback_binarized
llama
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2305.18290
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
00148cc
SmollerLM-20M-Instruct-Pruned-sft5-dpo3
1 contributor
History:
24 commits
mehmetkeremturkcan
Training in progress, step 11649
00148cc
verified
about 8 hours ago
runs
Training in progress, step 11649
about 8 hours ago
.gitattributes
Safe
1.52 kB
initial commit
about 13 hours ago
config.json
Safe
954 Bytes
Training in progress, step 1000
about 13 hours ago
merges.txt
Safe
466 kB
Training in progress, step 1000
about 13 hours ago
model.safetensors
Safe
57.1 MB
LFS
Training in progress, step 11649
about 8 hours ago
special_tokens_map.json
Safe
655 Bytes
Training in progress, step 1000
about 13 hours ago
tokenizer.json
Safe
3.52 MB
Training in progress, step 1000
about 13 hours ago
tokenizer_config.json
Safe
3.84 kB
Training in progress, step 1000
about 13 hours ago
training_args.bin
pickle
Detected Pickle imports (11)
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.OptimizerNames"
,
"trl.trainer.dpo_config.DPOConfig"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.SaveStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
How to fix it?
6.33 kB
LFS
Training in progress, step 1000
about 13 hours ago
vocab.json
Safe
801 kB
Training in progress, step 1000
about 13 hours ago
