Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
hZzy
/
qwen2.5-0.5b-expo-DPO-ES-0.1
like
0
Safetensors
hZzy/train_pairwise_weighted
qwen2
alignment-handbook
ndcg
trl
expo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
qwen2.5-0.5b-expo-DPO-ES-0.1
1.99 GB
1 contributor
History:
41 commits
This model has 1 file scanned as suspicious.
Show
files
hZzy
End of training
ee26d68
verified
12 months ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
README.md
4.3 kB
End of training
12 months ago
added_tokens.json
605 Bytes
Training in progress, step 50
about 1 year ago
all_results.json
795 Bytes
End of training
12 months ago
config.json
759 Bytes
End of training
12 months ago
eval_results.json
597 Bytes
End of training
12 months ago
generation_config.json
143 Bytes
Model save
12 months ago
merges.txt
1.67 MB
Training in progress, step 50
about 1 year ago
model.safetensors
1.98 GB
xet
Model save
12 months ago
special_tokens_map.json
509 Bytes
Training in progress, step 50
about 1 year ago
tokenizer.json
7.03 MB
Training in progress, step 50
about 1 year ago
tokenizer_config.json
4.86 kB
Training in progress, step 50
about 1 year ago
train_results.json
233 Bytes
Model save
12 months ago
trainer_state.json
14.7 kB
Model save
12 months ago
training_args.bin
8.12 kB
xet
Training in progress, step 50
12 months ago
vocab.json
2.78 MB
Training in progress, step 50
about 1 year ago