metadata
license: apache-2.0
language:
- en
metrics:
- accuracy
base_model:
- unsloth/phi-4
library_name: transformers
tags:
- text-generation-inference
- reinforcement-learning
- trl
- vllm
- datasets
Model
- Developed by: DARJYO
- Base Type: Fine-tuned language model
- Finetuned model : persadian_14B-GRPO
- Base Architecture: Transformer-based/Phi-4
This model is fine-tuned on datasets for tasks with Unsloth and Huggingface's TRL library.
It is based on the unsloth/Phi-4 model and uses reinforcement learning for improved performance.
