Instructions to use NebulaByte/hindi_gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NebulaByte/hindi_gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="NebulaByte/hindi_gpt2")

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

tokenizer = AutoTokenizer.from_pretrained("NebulaByte/hindi_gpt2")
model = AutoModelForCausalLM.from_pretrained("NebulaByte/hindi_gpt2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NebulaByte/hindi_gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NebulaByte/hindi_gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NebulaByte/hindi_gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NebulaByte/hindi_gpt2

SGLang

How to use NebulaByte/hindi_gpt2 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 "NebulaByte/hindi_gpt2" \
    --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": "NebulaByte/hindi_gpt2",
		"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 "NebulaByte/hindi_gpt2" \
        --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": "NebulaByte/hindi_gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NebulaByte/hindi_gpt2 with Docker Model Runner:
```
docker model run hf.co/NebulaByte/hindi_gpt2
```

hindi_gpt2

Commit History

Aug 2, 2023

09:06
Adding `safetensors` variant of this model⁠

SFconvertbot

c0d158c
06:45
Update README.md

NebulaByte

1f62b22
06:42
Upload model

NebulaByte

6e694aa

Aug 1, 2023

11:26
Update README.md

NebulaByte

d2dbb5d
11:23
update model card README.md

NebulaByte

833b100
11:22
Model save

NebulaByte

d0e2be6
11:01
Training in progress, step 2000

NebulaByte

41a9f5b
10:40
Training in progress, step 1600

NebulaByte

c0522af
10:19
Training in progress, step 1200

NebulaByte

0e8bad9
09:57
Training in progress, step 800

NebulaByte

3f66cbb
09:36
Training in progress, step 400

NebulaByte

a1019f2

Jul 24, 2023

11:52
Update README.md

NebulaByte

6cfc1c0
11:24
Update README.md

NebulaByte

ac6e6d2
11:19
Update README.md

NebulaByte

877dc85
11:05
Update README.md

NebulaByte

8a9e97d
10:23
Upload tokenizer

NebulaByte

ffd315f
10:23
Upload model

NebulaByte

cdcd519
10:13
initial commit

NebulaByte

1acd2e2

Commit History

Aug 2, 2023

Adding `safetensors` variant of this model⁠

Update README.md

Upload model

Aug 1, 2023

Update README.md

update model card README.md

Model save

Training in progress, step 2000

Training in progress, step 1600

Training in progress, step 1200

Training in progress, step 800

Training in progress, step 400

Jul 24, 2023

Update README.md

Update README.md

Update README.md

Update README.md

Upload tokenizer

Upload model

initial commit