---
language:
- en
tags:
- causal-lm
- llama
- point-in-time
- dated
- lookahead-bias-free
pipeline_tag: text-generation
---

# DatedGPT-2019 (base)

**DatedGPT** is a family of point-in-time language models: each vintage is
trained only on data available up to its cutoff date, making it suitable for
lookahead-bias-free prediction and point-in-time analysis.

This is the **base (pretrained) model** with data up to **2019** — no
instruction tuning. For the instruction-tuned variants, see the
`datedgpt-instruct-*` repositories in this organization.

| Property | Value |
|----------|-------|
| Architecture | LlamaForCausalLM |
| Parameters | ~1.3 B |
| Context length | 2048 |
| Vocab | 32,000 (SentencePiece) |
| Precision | bfloat16 |
| Data vintage | 2019 |

## Usage

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "datedgpt/datedgpt-2019-base"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map="auto")

inputs = tokenizer("The stock market in 2019", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=64, use_cache=True)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```

## Limitations

- Base model: completions only, no chat/instruction following.
- Knowledge limited to the 2019 data vintage.
- No RLHF or safety tuning.