datedgpt/datedgpt-2024-base

DatedGPT-2024 (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 2024 — 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	2024

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "datedgpt/datedgpt-2024-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 2024", 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 2024 data vintage.
• No RLHF or safety tuning.