Instructions to use thrunlab/gpt2-medium_gated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thrunlab/gpt2-medium_gated with Transformers:

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

pipe = pipeline("text-generation", model="thrunlab/gpt2-medium_gated")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thrunlab/gpt2-medium_gated")
model = AutoModelForCausalLM.from_pretrained("thrunlab/gpt2-medium_gated", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thrunlab/gpt2-medium_gated with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/thrunlab/gpt2-medium_gated

SGLang

How to use thrunlab/gpt2-medium_gated 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 "thrunlab/gpt2-medium_gated" \
    --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": "thrunlab/gpt2-medium_gated",
		"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 "thrunlab/gpt2-medium_gated" \
        --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": "thrunlab/gpt2-medium_gated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thrunlab/gpt2-medium_gated with Docker Model Runner:
```
docker model run hf.co/thrunlab/gpt2-medium_gated
```

gpt2-medium_gated

Commit History

Oct 20, 2025

01:53
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
27c7d9a

Sep 10, 2023

16:11
Training in progress, step 11000

vxbrandon

de9791b
16:08
Training in progress, step 10500

vxbrandon

33b2945
16:06
Training in progress, step 10000

vxbrandon

a0b04b8
16:03
Training in progress, step 9500

vxbrandon

8e233df
16:01
Training in progress, step 9000

vxbrandon

96af1d8
15:58
Training in progress, step 8500

vxbrandon

9437298
15:55
Training in progress, step 8000

vxbrandon

eef8678
15:53
Training in progress, step 7500

vxbrandon

482bb18
15:50
Training in progress, step 7000

vxbrandon

0a35f64
15:45
Training in progress, step 6000

vxbrandon

db3c4bb
15:40
Training in progress, step 5000

vxbrandon

0862761
15:38
Training in progress, step 4500

vxbrandon

6f66e2b
15:33
Training in progress, step 3500

vxbrandon

8bc63c1
15:30
Training in progress, step 3000

vxbrandon

f501cac
15:25
Training in progress, step 2000

vxbrandon

e19d166
15:22
Training in progress, step 1500

vxbrandon

b0958cc
15:20
Training in progress, step 1000

vxbrandon

9409220
15:17
Training in progress, step 500

vxbrandon

b78a838
11:05
Training in progress, step 15000

vxbrandon

c7902e1
11:03
Training in progress, step 14500

vxbrandon

1f678bc
11:00
Training in progress, step 14000

vxbrandon

18771ff
10:57
Training in progress, step 13500

vxbrandon

e7f6ac2
10:55
Training in progress, step 13000

vxbrandon

6f132c8
10:52
Training in progress, step 12500

vxbrandon

f6f26e4
10:50
Training in progress, step 12000

vxbrandon

57836b0
10:47
Training in progress, step 11500

vxbrandon

436ddaf
10:44
Training in progress, step 11000

vxbrandon

eb70e19
10:42
Training in progress, step 10500

vxbrandon

232271c
10:39
Training in progress, step 10000

vxbrandon

49bb4e5
10:37
Training in progress, step 9500

vxbrandon

ba0b566
10:34
Training in progress, step 9000

vxbrandon

1320655
10:29
Training in progress, step 8000

vxbrandon

95ab223
10:26
Training in progress, step 7500

vxbrandon

d1e716e
10:24
Training in progress, step 7000

vxbrandon

b98080e
10:21
Training in progress, step 6500

vxbrandon

e3da00b
10:19
Training in progress, step 6000

vxbrandon

b940a5d
10:16
Training in progress, step 5500

vxbrandon

7579749
10:14
Training in progress, step 5000

vxbrandon

bddb8e9
10:11
Training in progress, step 4500

vxbrandon

8e8e002
10:09
Training in progress, step 4000

vxbrandon

87ccb27
10:06
Training in progress, step 3500

vxbrandon

e2cc070
10:03
Training in progress, step 3000

vxbrandon

1da178b
10:01
Training in progress, step 2500

vxbrandon

6c9e24b
09:58
Training in progress, step 2000

vxbrandon

b035fd6
09:56
Training in progress, step 1500

vxbrandon

4558af4
09:53
Training in progress, step 1000

vxbrandon

4c957be
09:51
Training in progress, step 500

vxbrandon

9127a21
09:47
initial commit

vxbrandon

ee08496

Commit History

Oct 20, 2025

Adding `safetensors` variant of this model⁠

Sep 10, 2023

Training in progress, step 11000

Training in progress, step 10500

Training in progress, step 10000

Training in progress, step 9500

Training in progress, step 9000

Training in progress, step 8500

Training in progress, step 8000

Training in progress, step 7500

Training in progress, step 7000

Training in progress, step 6000

Training in progress, step 5000

Training in progress, step 4500

Training in progress, step 3500

Training in progress, step 3000

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

Training in progress, step 15000

Training in progress, step 14500

Training in progress, step 14000

Training in progress, step 13500

Training in progress, step 13000

Training in progress, step 12500

Training in progress, step 12000

Training in progress, step 11500

Training in progress, step 11000

Training in progress, step 10500

Training in progress, step 10000

Training in progress, step 9500

Training in progress, step 9000

Training in progress, step 8000

Training in progress, step 7500

Training in progress, step 7000

Training in progress, step 6500

Training in progress, step 6000

Training in progress, step 5500

Training in progress, step 5000

Training in progress, step 4500

Training in progress, step 4000

Training in progress, step 3500

Training in progress, step 3000

Training in progress, step 2500

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

initial commit