Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
moodlep
/
smollm2-17b-dpo-cai-v1
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
HuggingFaceH4/cai-conversation-harmless
llama
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
b1e40b1
smollm2-17b-dpo-cai-v1
1 contributor
History:
2 commits
moodlep
Training in progress, step 100
b1e40b1
verified
11 days ago
runs
Training in progress, step 100
11 days ago
.gitattributes
1.52 kB
initial commit
11 days ago
adapter_config.json
809 Bytes
Training in progress, step 100
11 days ago
adapter_model.safetensors
72.4 MB
LFS
Training in progress, step 100
11 days ago
merges.txt
466 kB
Training in progress, step 100
11 days ago
special_tokens_map.json
655 Bytes
Training in progress, step 100
11 days ago
tokenizer.json
3.52 MB
Training in progress, step 100
11 days ago
tokenizer_config.json
3.85 kB
Training in progress, step 100
11 days ago
training_args.bin
pickle
Detected Pickle imports (10)
"torch.device"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"transformers.training_args.OptimizerNames"
,
"alignment.configs.DPOConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.IntervalStrategy"
How to fix it?
6.01 kB
LFS
Training in progress, step 100
11 days ago
vocab.json
801 kB
Training in progress, step 100
11 days ago