Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ondevicellm
/
tinyllama_moe_dpo_ultrachat_v2_epochs3
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mixtral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
d5c4d66
tinyllama_moe_dpo_ultrachat_v2_epochs3
1 contributor
History:
2 commits
hushell
Training in progress, step 100
d5c4d66
verified
8 months ago
runs
Training in progress, step 100
8 months ago
.gitattributes
1.52 kB
initial commit
8 months ago
config.json
864 Bytes
Training in progress, step 100
8 months ago
special_tokens_map.json
550 Bytes
Training in progress, step 100
8 months ago
tokenizer.json
1.84 MB
Training in progress, step 100
8 months ago
tokenizer_config.json
1.42 kB
Training in progress, step 100
8 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"alignment.configs.DPOConfig"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"accelerate.state.PartialState"
,
"torch.bfloat16"
How to fix it?
6.07 kB
LFS
Training in progress, step 100
8 months ago