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

Libraries

How to use sekarmulyani/gpt2-ulasan-ecommerce with Transformers:

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

pipe = pipeline("text-generation", model="sekarmulyani/gpt2-ulasan-ecommerce")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sekarmulyani/gpt2-ulasan-ecommerce")
model = AutoModelForCausalLM.from_pretrained("sekarmulyani/gpt2-ulasan-ecommerce")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sekarmulyani/gpt2-ulasan-ecommerce with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sekarmulyani/gpt2-ulasan-ecommerce

SGLang

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

Docker Model Runner
How to use sekarmulyani/gpt2-ulasan-ecommerce with Docker Model Runner:
```
docker model run hf.co/sekarmulyani/gpt2-ulasan-ecommerce
```

Epoch	Training Loss	Validation Loss	Perplexity
1	3.450200	3.380510
2	3.309700	3.281852
3	3.238600	3.230116
4	3.200200	3.195386
5	3.148400	3.170542
6	3.125000	3.151122	23.36
7	3.102700	3.136005
8	3.091500	3.123388
9	3.067200	3.112496
10	3.057800	3.103361
11	3.039200	3.095544
12	3.023500	3.088650	21.95
13	3.012200	3.082917
14	3.009600	3.077587
15	2.998100	3.073186
16	2.987500	3.069203
17	2.975100	3.065609
18	2.974400	3.062548	21.38
19	2.969300	3.059562
20	2.956800	3.057292
21	2.950900	3.054723
22	2.952200	3.052954
23	2.944300	3.051039
24	2.939600	3.049278	21.10
25	2.923400	3.047985
26	2.919100	3.046863
27	2.932800	3.045910
28	2.922700	3.045190
29	2.917000	3.044068
30	2.922100	3.043669	20.98
31	2.910200	3.043278
32	2.911400	3.042759
33	2.913500	3.042451
34	2.902300	3.042186
35	2.914200	3.042054
36	2.905900	3.042003	20.95

Downloads last month: 2

sekarmulyani
/

gpt2-ulasan-ecommerce

Spaces using sekarmulyani/gpt2-ulasan-ecommerce 2