lakhera2023's picture
Upload folder using huggingface_hub
f73f47e verified
metadata
license: llama3
base_model: meta-llama/Llama-4-Scout-17B-16E
tags:
  - llama4
  - moe
  - torchtitan
  - custom

Llama 4 Debug Model - Trained with TorchTitan

Custom-trained Llama 4 model using TorchTitan framework.

Model Details

  • Training Framework: TorchTitan
  • Training Steps: 10,000
  • Model Size: ~220 MB
  • Precision: bfloat16

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("lakhera2023/llama4-debugmodel-10k") tokenizer = AutoTokenizer.from_pretrained("lakhera2023/llama4-debugmodel-10k")

prompt = "Once upon a time" inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=100) print(tokenizer.decode(outputs[0]))