---
datasets:
- roneneldan/TinyStories
---
---
Model trained on the TinyStories Dataset, replicating https://arxiv.org/abs/2305.07759, based on GPT-Neo architecture.

---
Hyperparams used to train this model:
```
        "batch_size": 64,
        "block_size": 128,
        "lr": 6e-4,
        "n_layer": 4,
        "n_head": 4,
        "n_embd": 64,
        "dropout": 0.1,
        "weight_decay": 0.01,
        "epochs": 1,
        "eval_interval": 200,
        "eval_steps": 50,
        "vocab_size": 50257,
        "warmup_tokens": 5000,
        "gradient_accumulation_steps": 16,
```
---
EXAMPLE USAGE 
```py
  !pip install --quiet transformers 
  from transformers import AutoModelForCausalLM, AutoTokenizer
  model = AutoModelForCausalLM.from_pretrained('AnirudhRajagopalan1201/tinystories-custom-3M')
  
  tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
  prompt = "Lily likes cats and dogs. She asked her mom for a dog and her mom said no, so instead she asked"
  input_ids = tokenizer.encode(prompt, return_tensors="pt") 
  output = model.generate(input_ids, temperature=0.2, max_length = 100, do_sample=True)
  output_text = tokenizer.decode(output[0], skip_special_tokens=True)
  print(output_text)
```