Instructions to use ichangzii/pit2022-gpt2-124m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ichangzii/pit2022-gpt2-124m with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ichangzii/pit2022-gpt2-124m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ichangzii/pit2022-gpt2-124m")
model = AutoModelForCausalLM.from_pretrained("ichangzii/pit2022-gpt2-124m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ichangzii/pit2022-gpt2-124m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ichangzii/pit2022-gpt2-124m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ichangzii/pit2022-gpt2-124m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ichangzii/pit2022-gpt2-124m

SGLang

How to use ichangzii/pit2022-gpt2-124m with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ichangzii/pit2022-gpt2-124m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ichangzii/pit2022-gpt2-124m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ichangzii/pit2022-gpt2-124m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ichangzii/pit2022-gpt2-124m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ichangzii/pit2022-gpt2-124m with Docker Model Runner:
```
docker model run hf.co/ichangzii/pit2022-gpt2-124m
```

PIT-GPT-2-124M — a point-in-time (≤2022) language model

GPT-2 (124 M) trained from scratch on only ≤2022 data, giving a certified lookahead-free knowledge cutoff. Built for reliable time-sensitive evaluation (e.g. trading backtests) where the model must not know the future — the cutoff is clean by construction (never trained on post-2022 text), not by unlearning or suppression.

Cutoff certification (causal-completion probe)

	mean p(answer)
POST-2022 (Threads, Sora, Gemini, DeepSeek, Bard, Grok, Llama, Mistral — should NOT know)	0.001
≤2022 (COVID 0.82, Ukraine 0.24, Brexit — should know)	0.136

The model has ~zero knowledge of unforeseen 2023+ entities. (Probe caveat: entities that existed or were speculated pre-2022 — e.g. GPT-4, Credit Suisse — leak via legitimate ≤2022 knowledge, not lookahead; those are excluded.)

Quality

WikiText-2 perplexity: 43.1 (random-init ≈ 50 000; fully-trained GPT-2-124 M ≈ 30–37)
Coherent, grammatical generation. 4.2 B tokens seen (past Chinchilla-optimal for 124 M; undertrained vs GPT-2's ~10 B → ppl ~43 not ~30).
loss_curve.csv and ppl_by_checkpoint.json included.

Training

Data: ichangzii/pit2022-10b (foundation) + ichangzii/pit2022-news (date-tagged), all ≤2022.
GPT-2 tokenizer, AdamW (β2 .95, wd .1, lr 6e-4, ~0.5 M batch), non-overlapping shuffled sampling, bf16, torch.compile. RTX 5090.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("ichangzii/pit2022-gpt2-124m")
tok = AutoTokenizer.from_pretrained("gpt2")

Limitations

Undertrained (4.2 B tokens) — a longer run (~10 B) would lower perplexity and strengthen ≤2022 knowledge.
Time-conditioning did not emerge — prepending Date: YYYY-MM-DD has no effect (date-tagged news was only ~4% of training). This is a single clean cutoff, not a queryable as-of-date model.

Downloads last month: 179

Safetensors

Model size

0.1B params

Tensor type

BF16

ichangzii
/

pit2022-gpt2-124m