Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
chchen
/
Mistral-7B-Instruct-v0.2-ORPO-SALT-HALF
like
0
PEFT
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
Mistral-7B-Instruct-v0.2-ORPO-SALT-HALF
86.6 MB
1 contributor
History:
6 commits
chchen
End of training
7221255
verified
over 1 year ago
.ipynb_checkpoints
Training in progress, step 500
over 1 year ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
README.md
2.78 kB
End of training
over 1 year ago
adapter_config.json
735 Bytes
Training in progress, step 500
over 1 year ago
adapter_model.safetensors
83.9 MB
xet
Training in progress, step 1500
over 1 year ago
all_results.json
837 Bytes
End of training
over 1 year ago
eval_results.json
650 Bytes
End of training
over 1 year ago
lora_orpo.yaml
880 Bytes
Training in progress, step 500
over 1 year ago
special_tokens_map.json
437 Bytes
Training in progress, step 500
over 1 year ago
tokenizer.json
1.8 MB
Training in progress, step 500
over 1 year ago
tokenizer.model
493 kB
xet
Training in progress, step 500
over 1 year ago
tokenizer_config.json
1.41 kB
Training in progress, step 500
over 1 year ago
train_results.json
222 Bytes
End of training
over 1 year ago
trainer_log.jsonl
42.5 kB
Model save
over 1 year ago
trainer_state.json
112 kB
End of training
over 1 year ago
training_args.bin
5.24 kB
xet
Training in progress, step 500
over 1 year ago
training_eval_loss.png
39.9 kB
End of training
over 1 year ago
training_loss.png
46.5 kB
End of training
over 1 year ago
training_rewards_accuracies.png
78.7 kB
End of training
over 1 year ago
training_sft_loss.png
46.8 kB
End of training
over 1 year ago
