Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
thobuiq
/
mistral-dpo
like
0
Text Generation
PEFT
Safetensors
mistral
Generated from Trainer
4-bit precision
gptq
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
72e761f
mistral-dpo
1 contributor
History:
3 commits
thobuiq
Create config.json
72e761f
verified
10 months ago
.gitattributes
Safe
1.52 kB
initial commit
10 months ago
README.md
Safe
6.68 kB
Upload 10 files
10 months ago
adapter_config.json
Safe
587 Bytes
Upload 10 files
10 months ago
adapter_model.safetensors
Safe
135 Bytes
LFS
Upload 10 files
10 months ago
added_tokens.json
Safe
51 Bytes
Upload 10 files
10 months ago
config.json
0 Bytes
Create config.json
10 months ago
special_tokens_map.json
Safe
630 Bytes
Upload 10 files
10 months ago
tokenizer.json
Safe
1.8 MB
Upload 10 files
10 months ago
tokenizer.model
Safe
493 kB
LFS
Upload 10 files
10 months ago
tokenizer_config.json
Safe
1.42 kB
Upload 10 files
10 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.TrainingArguments"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
How to fix it?
4.22 kB
LFS
Upload 10 files
10 months ago
