Instructions to use Imran1/gpt2-urdu-news with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Imran1/gpt2-urdu-news with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Imran1/gpt2-urdu-news")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Imran1/gpt2-urdu-news") model = AutoModelForCausalLM.from_pretrained("Imran1/gpt2-urdu-news", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Imran1/gpt2-urdu-news with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Imran1/gpt2-urdu-news" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Imran1/gpt2-urdu-news", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Imran1/gpt2-urdu-news
- SGLang
How to use Imran1/gpt2-urdu-news 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 "Imran1/gpt2-urdu-news" \ --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": "Imran1/gpt2-urdu-news", "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 "Imran1/gpt2-urdu-news" \ --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": "Imran1/gpt2-urdu-news", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Imran1/gpt2-urdu-news with Docker Model Runner:
docker model run hf.co/Imran1/gpt2-urdu-news
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ tokenizer = AutoTokenizer.from_pretrained("Imran1/gpt2-urdu-news")
|
|
| 25 |
model = AutoModelForCausalLM.from_pretrained("Imran1/gpt2-urdu-news")
|
| 26 |
```
|
| 27 |
## Training data
|
| 28 |
-
I fine tune gpt2 for downstream task like text generation, only for 1000 sample so it may not be good
|
| 29 |
|
| 30 |
|
| 31 |
## Evaluation results
|
|
|
|
| 25 |
model = AutoModelForCausalLM.from_pretrained("Imran1/gpt2-urdu-news")
|
| 26 |
```
|
| 27 |
## Training data
|
| 28 |
+
I fine tune gpt2 for downstream task like text generation, only for 1000 sample so it may not be good. Due to resources limitation.
|
| 29 |
|
| 30 |
|
| 31 |
## Evaluation results
|