aksheyd
/

llama-3.1-8b-instruct-no-robots

Text Generation

Model card Files Files and versions

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

Please see this repo for additional details.

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

BF16

·

Model tree for aksheyd/llama-3.1-8b-instruct-no-robots

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2049)

this model

Quantizations

1 model

Dataset used to train aksheyd/llama-3.1-8b-instruct-no-robots