Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
bartowski
/
zephyr-7b-dpo-full-exl2
like
1
Text Generation
HuggingFaceH4/ultrafeedback_binarized
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
b6a902a
zephyr-7b-dpo-full-exl2
1 contributor
History:
3 commits
bartowski
Quant for 8.0
b6a902a
verified
9 months ago
.gitattributes
1.52 kB
initial commit
9 months ago
README.md
2.87 kB
Quant for 8.0
9 months ago
all_results.json
737 Bytes
Quant for 8.0
9 months ago
config.json
654 Bytes
Quant for 8.0
9 months ago
eval_results.json
562 Bytes
Quant for 8.0
9 months ago
generation_config.json
111 Bytes
Quant for 8.0
9 months ago
measurement.json
1.79 MB
measurement.json
9 months ago
model.safetensors.index.json
24 kB
Quant for 8.0
9 months ago
original_repo_url.txt
61 Bytes
Quant for 8.0
9 months ago
output.safetensors
7.37 GB
LFS
Quant for 8.0
9 months ago
special_tokens_map.json
551 Bytes
Quant for 8.0
9 months ago
tokenizer.json
1.8 MB
Quant for 8.0
9 months ago
tokenizer_config.json
1.39 kB
Quant for 8.0
9 months ago
train_results.json
195 Bytes
Quant for 8.0
9 months ago
trainer_state.json
25.8 kB
Quant for 8.0
9 months ago