Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
chchen
/
Llama-3.1-8B-Instruct-KTO-200
like
0
PEFT
Safetensors
llama-factory
lora
trl
kto
Generated from Trainer
License:
llama3.1
Model card
Files
Files and versions
xet
Community
Use this model
main
Llama-3.1-8B-Instruct-KTO-200
101 MB
1 contributor
History:
8 commits
chchen
End of training
ff41cc4
verified
about 1 year ago
.gitattributes
1.57 kB
Training in progress, step 50
about 1 year ago
README.md
2.75 kB
End of training
about 1 year ago
adapter_config.json
738 Bytes
Training in progress, step 50
about 1 year ago
adapter_model.safetensors
83.9 MB
xet
Model save
about 1 year ago
all_results.json
715 Bytes
End of training
about 1 year ago
eval_results.json
526 Bytes
End of training
about 1 year ago
llama3_lora_kto.yaml
909 Bytes
Training in progress, step 50
about 1 year ago
special_tokens_map.json
650 Bytes
Training in progress, step 50
about 1 year ago
tokenizer.json
17.2 MB
xet
Training in progress, step 50
about 1 year ago
tokenizer_config.json
55.5 kB
Training in progress, step 50
about 1 year ago
train_results.json
223 Bytes
End of training
about 1 year ago
trainer_log.jsonl
5.08 kB
Training in progress, step 220
about 1 year ago
trainer_state.json
14.6 kB
End of training
about 1 year ago
training_args.bin
5.62 kB
xet
Training in progress, step 50
about 1 year ago
training_eval_loss.png
41.9 kB
End of training
about 1 year ago
training_loss.png
40 kB
End of training
about 1 year ago
training_rewards_chosen.png
46 kB
End of training
about 1 year ago
