LLaMA3 / README.md
parkneurals's picture
Update README.md
6b702e5 verified
metadata
language: en
license: mit
library_name: jax
tags:
  - llama
  - text-generation
  - shakespeare
model_name: LLaMA3
base_model: llama

LLaMA3

custom Llama-based model trained on tiny shakespeare text using JAX.

Model Details

  • Architecture: Llama-based Transformer
  • Parameters: ~31.6M
  • Training Framework: JAX
  • Tokenization: GPT-2 Encoding (tiktoken)

How to use

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("parkneurals/LLaMA3")