Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Evan-Lin
/
positive-chosen-llama-chat-without-none
like
0
PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
xet
Community
Use this model
main
positive-chosen-llama-chat-without-none
27.5 MB
1 contributor
History:
6 commits
Evan-Lin
Evan-Lin/dpo-llama-chat
5ec1e42
verified
about 2 years ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 years ago
README.md
Safe
3.9 kB
Evan-Lin/dpo-llama-chat
about 2 years ago
adapter_config.json
Safe
672 Bytes
Evan-Lin/dpo-llama-chat
about 2 years ago
adapter_model.safetensors
25.2 MB
xet
Evan-Lin/dpo-llama-chat
about 2 years ago
special_tokens_map.json
Safe
437 Bytes
Evan-Lin/dpo-llama-chat
about 2 years ago
tokenizer.json
Safe
1.84 MB
Evan-Lin/dpo-llama-chat
about 2 years ago
tokenizer.model
Safe
500 kB
xet
Evan-Lin/dpo-llama-chat
about 2 years ago
tokenizer_config.json
Safe
1.76 kB
Evan-Lin/dpo-llama-chat
about 2 years ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
,
"transformers.training_args.TrainingArguments"
How to fix it?
4.73 kB
xet
Evan-Lin/dpo-llama-chat
about 2 years ago