ReAction 1.5B

ReAction 1.5B is a fine-tuned version of Qwen/Qwen2.5-1.5B specifically optimized rewriting video descriptions in clearer wording.

IMPORTANT: Please ensure you are using the following sampler settings for optimal results:

temperature = 0.7
frequency_penalty = 0.0
presence_penalty = 0.0
min_p = 0.01
top_p = 0.95
top_k = 40

Model Details

Developed by: qingy2024

Finetuned from model: Qwen/Qwen2.5-1.5B

Model type: Qwen 2.5

Language(s): English

License: apache-2.0

Training Dataset: qingy2024/webvid-10M-classified


Contact

For questions or issues related to the model, please reach out via Hugging Face or by creating an issue in the repository.

Downloads last month
21
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for qingy2024/ReAction-1.5B

Base model

Qwen/Qwen2.5-1.5B
Finetuned
(142)
this model
Quantizations
2 models

Dataset used to train qingy2024/ReAction-1.5B