Agnuxo/Tinytron-codegemma-2b-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bit

Uploaded model

• Developed by: Agnuxo
• License: apache-2.0
• Finetuned from model : google/codegemma-1.1-2b

This Mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Benchmark Results

This model has been fine-tuned for various tasks and evaluated on the following benchmarks:

GLUE SST-2

Accuracy: 0.5356

Model Size: 2,506,176,512 parameters Required Memory: 9.34 GB

For more details, visit my GitHub.

Thanks for your interest in this model!