Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chchen
/
Llama-3.1-8B-Instruct-ppo-500
like
0
PEFT
Safetensors
arxiv:
1910.09700
Model card
Files
Files and versions
Community
Use this model
ede28fe
Llama-3.1-8B-Instruct-ppo-500
1 contributor
History:
2 commits
chchen
Upload 13 files
ede28fe
verified
3 days ago
.gitattributes
1.57 kB
Upload 13 files
3 days ago
README.md
5.11 kB
Upload 13 files
3 days ago
adapter_config.json
733 Bytes
Upload 13 files
3 days ago
adapter_model.safetensors
83.9 MB
LFS
Upload 13 files
3 days ago
llama3_lora_ppo.yaml
878 Bytes
Upload 13 files
3 days ago
special_tokens_map.json
650 Bytes
Upload 13 files
3 days ago
tokenizer.json
17.2 MB
LFS
Upload 13 files
3 days ago
tokenizer_config.json
55.5 kB
Upload 13 files
3 days ago
trainer_log.jsonl
2.95 kB
Upload 13 files
3 days ago
trainer_state.json
2.63 kB
Upload 13 files
3 days ago
training_args.bin
pickle
Detected Pickle imports (9)
"llamafactory.hparams.training_args.TrainingArguments"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
How to fix it?
5.56 kB
LFS
Upload 13 files
3 days ago
training_loss.png
34 kB
Upload 13 files
3 days ago
training_reward.png
38.9 kB
Upload 13 files
3 days ago
value_head.safetensors
16.6 kB
LFS
Upload 13 files
3 days ago