Instructions to use EleutherAI/GPT-2-wikitext-chunks with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/GPT-2-wikitext-chunks with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/GPT-2-wikitext-chunks")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/GPT-2-wikitext-chunks")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/GPT-2-wikitext-chunks", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/GPT-2-wikitext-chunks with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/GPT-2-wikitext-chunks"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/GPT-2-wikitext-chunks",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/GPT-2-wikitext-chunks

SGLang

How to use EleutherAI/GPT-2-wikitext-chunks 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 "EleutherAI/GPT-2-wikitext-chunks" \
    --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": "EleutherAI/GPT-2-wikitext-chunks",
		"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 "EleutherAI/GPT-2-wikitext-chunks" \
        --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": "EleutherAI/GPT-2-wikitext-chunks",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/GPT-2-wikitext-chunks with Docker Model Runner:
```
docker model run hf.co/EleutherAI/GPT-2-wikitext-chunks
```

GPT-2-wikitext-chunks / README.md

luciaquirke

Upload README.md with huggingface_hub

8bbd516 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.29 kB

metadata

license: mit
base_model: gpt2
datasets:
  - EleutherAI/bergson-wikitext-512-chunks
library_name: transformers
pipeline_tag: text-generation

GPT-2 fine-tuned on bergson-wikitext-512-chunks

GPT-2 (124M) fine-tuned on EleutherAI/bergson-wikitext-512-chunks (WikiText-2 pre-chunked to 512-token sequences, 4,608 train chunks) using the bergson MAGIC trainer, as the trained model for MAGIC attribution experiments.

Training

4 epochs, global batch size 64 (8x data parallel), 288 steps
AdamW, polynomial LR schedule: lr 8e-4 (start 1e-6, end 8e-5), 25% warmup, fp32
Loss on held-out test[:4] chunks: 3.22 (base gpt2: 3.62)

Files

Standard HF model + tokenizer files
bergson_config.yaml — the fully-resolved bergson run config (all fields incl. defaults) that produced this model; rerun with python -m bergson bergson_config.yaml
optimizer.pt — AdamW second moments (exp_avg_sq) at the final training step, in bergson's optimizer.pt normalizer format ({"state": {idx: {"exp_avg_sq": ...}}, "param_groups": [...]} with idx indexing deduplicated model.named_parameters()), for gradient normalization in attribution runs.