Edit model card

Uploaded model

  • Developed by: acbdkk
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit

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

Note: PLEASE use Unsloth. It is 2X FASTER and llama-3-8b can even be fine-tuned FOR FREE in google colab! Additionally, Codellama-34b can be fine-tuned inside AN A100 in google colab! There is simply no excuse not to use Unsloth.

Downloads last month
8
Safetensors
Model size
4.46B params
Tensor type
FP16
F32
U8
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for acbdkk/SupaMATH

Quantized
(679)
this model

Space using acbdkk/SupaMATH 1