---
license: apache-2.0
base_model:
- meta-llama/Llama-3.1-8B-Instruct
datasets:
- HuggingFaceH4/no_robots
language:
- en
metrics:
- accuracy
pipeline_tag: text-generation
---

# aksheyd/llama-3.1-8b-instruct-no-robots

Llama-3.1-8B-Instruct SFT via No Robots dataset using Tinker and LoRA (rank=32). 

Quantized to 4 bits for MLX [here](https://huggingface.co/aksheyd/llama-3.1-8b-instruct-no-robots-mlx)

Please see this [repo](https://github.com/aksheyd/easy-train) for additional details.