Llama-3.2-3B-4bit / README.md
codewithdark's picture
Upload model via QuantLLM
97dcc8c verified
metadata
base_model: Llama-3.2-3B
library_name: quantllm
tags:
  - quantllm
  - generated_from_trainer

Llama-3.2-3B-4bit

This model was fine-tuned using QuantLLM.

Hyperparameters

The following hyperparameters were used during training:

  • format: gguf
  • base_model: Llama-3.2-3B