Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Nekochu
/
Llama-3.1-8B-french-DPO
like
1
PEFT
Safetensors
6 datasets
French
English
llama
llama-factory
lora
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Use this model
83361eb
Llama-3.1-8B-french-DPO
/
QLoRA_french_dpo
1 contributor
History:
1 commit
Nekochu
Add QLoRA_french_dpo
6eca494
verified
6 months ago
adapter_config.json
Safe
775 Bytes
Add QLoRA_french_dpo
6 months ago
adapter_model.safetensors
Safe
336 MB
LFS
Add QLoRA_french_dpo
6 months ago
all_results.json
Safe
215 Bytes
Add QLoRA_french_dpo
6 months ago
special_tokens_map.json
Safe
342 Bytes
Add QLoRA_french_dpo
6 months ago
tokenizer.json
Safe
9.09 MB
Add QLoRA_french_dpo
6 months ago
tokenizer_config.json
Safe
53.2 kB
Add QLoRA_french_dpo
6 months ago
train_results.json
Safe
215 Bytes
Add QLoRA_french_dpo
6 months ago
trainer_log.jsonl
Safe
253 kB
Add QLoRA_french_dpo
6 months ago
trainer_state.json
Safe
515 kB
Add QLoRA_french_dpo
6 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
How to fix it?
5.37 kB
LFS
Add QLoRA_french_dpo
6 months ago
training_loss.png
Safe
40.7 kB
Add QLoRA_french_dpo
6 months ago
training_rewards_accuracies.png
Safe
44.2 kB
Add QLoRA_french_dpo
6 months ago
