metadata
base_model: Pinkstack/Fijik-3b-sft
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- dpo
license: apache-2.0
language:
- en
Uploaded model
- Developed by: Pinkstack
- License: apache-2.0
- Finetuned from model : Pinkstack/Fijik-3b-sft
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
