Agente-Director-Qwen2-7Bron-Instruct_CODE_Python_English_GGUF_16bit
- Developed by: Agnuxo
- License: apache-2.0
- Finetuned from model: Qwen/Qwen2-7B-Instruct
This model was fine-tuned using Unsloth and Huggingface's TRL library.
Model Details
- Model Parameters: 7070.63 million
- Model Size: 13.61 GB
- Quantization: 16-bit quantized
- Estimated GPU Memory Required: ~13 GB
Note: The actual memory usage may vary depending on the specific hardware and runtime environment.
Benchmark Results
This model has been fine-tuned and evaluated on the GLUE MRPC task:
- Accuracy: 0.4730
- F1 Score: 0.4917
For more details, visit my GitHub.
Thanks for your interest in this model!
- Downloads last month
- 36
Evaluation results
- Accuracy on gluevalidation set self-reported0.473
- F1 on gluevalidation set self-reported0.492