Edit model card

Uploaded model

  • Developed by: inflaton
  • License: apache-2.0
  • Finetuned from model : gradientai/Llama-3-8B-Instruct-Gradient-1048k

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

Downloads last month
2,288
Safetensors
Model size
4.69B params
Tensor type
BF16
F32
U8
Inference API
Input a message to start chatting with inflaton/Llama-3-8B-Instruct-Gradient-1048k-MAC-lora.
This model can be loaded on Inference API (serverless).

Quantized from