Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
GeorgiaTech
/
0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3
like
0
Follow
Georgia Institute of Technology
2.32k
Text Generation
Transformers
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3
14.5 GB
1 contributor
History:
3 commits
ZhangShenao
End of training
94b1bed
verified
over 1 year ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
README.md
1.56 kB
End of training
over 1 year ago
all_results.json
230 Bytes
Model save
over 1 year ago
config.json
682 Bytes
End of training
over 1 year ago
generation_config.json
111 Bytes
Model save
over 1 year ago
model-00001-of-00003.safetensors
4.94 GB
xet
Model save
over 1 year ago
model-00002-of-00003.safetensors
5 GB
xet
Model save
over 1 year ago
model-00003-of-00003.safetensors
4.54 GB
xet
Model save
over 1 year ago
model.safetensors.index.json
24 kB
Model save
over 1 year ago
special_tokens_map.json
624 Bytes
Model save
over 1 year ago
tokenizer.json
1.8 MB
Model save
over 1 year ago
tokenizer.model
493 kB
xet
Model save
over 1 year ago
tokenizer_config.json
1.46 kB
Model save
over 1 year ago
train_results.json
230 Bytes
Model save
over 1 year ago
trainer_state.json
4.4 kB
Model save
over 1 year ago
training_args.bin
6.33 kB
xet
Model save
over 1 year ago