Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
kyynaama
/
Ahma-3B-toxic-dpo-qlora
like
0
Safetensors
Model card
Files
Files and versions
Community
71e4193
Ahma-3B-toxic-dpo-qlora
1 contributor
History:
3 commits
kyynaama
Create README.md
71e4193
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
README.md
31 Bytes
Create README.md
3 months ago
adapter_config.json
712 Bytes
Upload folder using huggingface_hub
3 months ago
adapter_model.safetensors
16 MB
LFS
Upload folder using huggingface_hub
3 months ago
special_tokens_map.json
437 Bytes
Upload folder using huggingface_hub
3 months ago
tokenizer.json
4.84 MB
Upload folder using huggingface_hub
3 months ago
tokenizer_config.json
2.9 kB
Upload folder using huggingface_hub
3 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"trl.trainer.dpo_config.DPOConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"__builtin__.getattr"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"torch.device"
How to fix it?
5.75 kB
LFS
Upload folder using huggingface_hub
3 months ago