skar0's picture
Upload tiny random Llama-3.3 model (seed 42)
32a6826 verified
|
raw
history blame
1.54 kB
metadata
license: mit
base_model: EleutherAI/pythia-14m
tags:
  - tiny-model
  - random-weights
  - testing
  - llama

Llama-3.3-Tiny-Instruct

This is a tiny random version of the EleutherAI/pythia-14m model, created for testing and experimentation purposes.

Model Details

  • Base model: EleutherAI/pythia-14m
  • Seed: 42
  • Hidden size: 64
  • Number of layers: 2
  • Number of attention heads: 2
  • Vocabulary size: 1000
  • Max position embeddings: 512

Parameters

  • Total parameters: ~195,072
  • Trainable parameters: ~195,072

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")
tokenizer = AutoTokenizer.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")

# Generate text (note: this model has random weights!)
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)
print(tokenizer.decode(outputs[0]))

Important Notes

⚠️ This model has random weights and is not trained! It's designed for:

  • Testing model loading and inference pipelines
  • Benchmarking model architecture
  • Educational purposes
  • Rapid prototyping where actual model performance isn't needed

The model will generate random/nonsensical text since it hasn't been trained on any data.

Creation

This model was created using the upload_tiny_llama33.py script from the minimal-grpo-trainer repository.