Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ComparisonPO
/
Mistral-Base-7B-DPO-ComPO
like
1
Follow
ComPO
3
Safetensors
trl-lib/ultrafeedback_binarized
mistral
License:
mit
Model card
Files
Files and versions
Community
README.md exists but content is empty.
Downloads last month
5
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Chat template
Files info
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.
Model tree for
ComparisonPO/Mistral-Base-7B-DPO-ComPO
Base model
mistralai/Mistral-7B-v0.1
Finetuned
alignment-handbook/zephyr-7b-sft-full
Finetuned
ComparisonPO/Mistral-Base-7B-DPO_clean
Finetuned
(
1
)
this model
Dataset used to train
ComparisonPO/Mistral-Base-7B-DPO-ComPO
trl-lib/ultrafeedback_binarized
Viewer
•
Updated
Sep 12, 2024
•
63.1k
•
7.5k
•
15
Collection including
ComparisonPO/Mistral-Base-7B-DPO-ComPO
DPOClean + ComPO
Collection
4 items
•
Updated
23 days ago
•
1