File size: 1,322 Bytes
71e3f07 5dadbeb 71e3f07 5dadbeb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
---
library_name: transformers
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": 32,
"block_size": 256,
"lr": 5e-4,
"n_layer": 6,
"n_head": 6,
"n_embd": 288,
"dropout": 0.1,
"weight_decay": 0.01,
"epochs": 1,
"eval_interval": 200,
"eval_steps": 50,
"vocab_size": 50257,
"warmup_tokens": 10000,
"gradient_accumulation_steps": 8
------ EXAMPLE USAGE ---
!pip install --quiet transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model20 = AutoModelForCausalLM.from_pretrained('AnirudhRajagopalan1201/tinystories-custom-20M')
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")
print("--------------20M parameter--------------------------------")
output = model20.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) |