Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
zfz1
/
deepseek-8b-dpo-full2
like
0
Text Generation
Transformers
TensorBoard
Safetensors
llama
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
12efc66
deepseek-8b-dpo-full2
1 contributor
History:
5 commits
zfz1
Training in progress, step 2000
12efc66
verified
3 months ago
runs
Training in progress, step 2000
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
config.json
749 Bytes
Training in progress, step 500
3 months ago
special_tokens_map.json
482 Bytes
Training in progress, step 500
3 months ago
tokenizer.json
4.61 MB
Training in progress, step 500
3 months ago
tokenizer_config.json
1.42 kB
Training in progress, step 500
3 months ago
training_args.bin
pickle
Detected Pickle imports (13)
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"alignment.configs.DPOConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"torch.bfloat16"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"transformers.trainer_utils.IntervalStrategy"
How to fix it?
7.22 kB
LFS
Training in progress, step 500
3 months ago