Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
QinLiuNLP
/
llama3-sudo-dpo-10epochs-forget10mixall-1sft-2lora-1e-5
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
llama3-sudo-dpo-10epochs-forget10mixall-1sft-2lora-1e-5
1 contributor
History:
4 commits
QinLiuNLP
Model save
10d8a09
verified
21 days ago
runs
Training in progress, step 1250
21 days ago
.gitattributes
1.52 kB
initial commit
21 days ago
README.md
1.42 kB
Model save
21 days ago
adapter_config.json
748 Bytes
Training in progress, step 1000
21 days ago
adapter_model.safetensors
671 MB
LFS
Training in progress, step 1250
21 days ago
all_results.json
216 Bytes
Model save
21 days ago
special_tokens_map.json
439 Bytes
Training in progress, step 1000
21 days ago
tokenizer.json
9.09 MB
Training in progress, step 1000
21 days ago
tokenizer_config.json
51 kB
Training in progress, step 1000
21 days ago
train_results.json
216 Bytes
Model save
21 days ago
trainer_state.json
64.9 kB
Model save
21 days ago
training_args.bin
7.67 kB
LFS
Training in progress, step 1000
21 days ago
