Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ondevicellm
/
tinyllama_mole_dpo_ep3
like
0
Follow
On-Device-LLM
4
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mixtralmole
alignment-handbook
trl
dpo
Generated from Trainer
conversational
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
ba60cc9
tinyllama_mole_dpo_ep3
1 contributor
History:
9 commits
hushell
Training in progress, step 800
ba60cc9
verified
about 1 year ago
runs
Training in progress, step 800
about 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 year ago
config.json
Safe
1.3 kB
Training in progress, step 100
about 1 year ago
model.safetensors
Safe
2.22 GB
LFS
Training in progress, step 800
about 1 year ago
special_tokens_map.json
Safe
550 Bytes
Training in progress, step 100
about 1 year ago
tokenizer.json
Safe
1.84 MB
Training in progress, step 100
about 1 year ago
tokenizer.model
Safe
500 kB
LFS
Training in progress, step 100
about 1 year ago
tokenizer_config.json
Safe
1.34 kB
Training in progress, step 100
about 1 year ago
training_args.bin
pickle
Detected Pickle imports (12)
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.bfloat16"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"configs.DPOConfig"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
How to fix it?
6.01 kB
LFS
Training in progress, step 100
about 1 year ago