metadata
base_model: qiqiquq/sft-reranker-step2000-1203
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- dpo
license: apache-2.0
language:
- en
Uploaded model
- Developed by: qiqiquq
- License: apache-2.0
- Finetuned from model : qiqiquq/sft-reranker-step2000-1203
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
