Views
No views yet
| Date | HF Checkpoint | Tokens | Step | HellaSwag Acc_norm |
|---|---|---|---|---|
| Baseline | StableLM-Alpha-3B | 800B | -- | 38.31 |
| Baseline | Pythia-1B-intermediate-step-50k-105b | 105B | 50k | 42.04 |
| Baseline | Pythia-1B | 300B | 143k | 47.16 |
| 2023-09-04 | TinyLlama-1.1B-intermediate-step-50k-105b | 105B | 50k | 43.50 |
| 2023-09-16 | -- | 500B | -- | -- |
| 2023-10-01 | -- | 1T | -- | -- |
| 2023-10-16 | -- | 1.5T | -- | -- |
| 2023-10-31 | -- | 2T | -- | -- |
| 2023-11-15 | -- | 2.5T | -- | -- |
| 2023-12-01 | -- | 3T | -- | -- |
from transformers import AutoTokenizer
import transformers
import torch
model = "TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.',
do_sample=True,
top_k=10,
num_return_sequences=1,
repetition_penalty=1.5,
eos_token_id=tokenizer.eos_token_id,
max_length=500,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")