Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
zfz1
/
deepseek-8b-orpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
zfz1/my_preference_gsm8k_deepseek
llama
alignment-handbook
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
other
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
b04eac5
deepseek-8b-orpo-full
1 contributor
History:
4 commits
zfz1
Training in progress, step 1250
b04eac5
verified
4 months ago
runs
Training in progress, step 1250
4 months ago
.gitattributes
1.52 kB
initial commit
4 months ago
config.json
727 Bytes
Training in progress, step 500
4 months ago
special_tokens_map.json
369 Bytes
Training in progress, step 500
4 months ago
tokenizer.json
4.61 MB
Training in progress, step 500
4 months ago
tokenizer_config.json
1.42 kB
Training in progress, step 500
4 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"alignment.configs.ORPOConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"torch.bfloat16"
,
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
How to fix it?
6.46 kB
LFS
Training in progress, step 500
4 months ago