Instructions to use thanhduc1180/qwen2.5-7b-finviqa-grpo-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thanhduc1180/qwen2.5-7b-finviqa-grpo-full with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("thanhduc1180/qwen2.5-7b-finviqa-grpo-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
metadata
base_model: SUFE-AIFLM-Lab/Fin-R1
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
Uploaded model
- Developed by: thanhduc1180
- License: apache-2.0
- Finetuned from model : SUFE-AIFLM-Lab/Fin-R1
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
