Instructions to use IBB-University/ghadeer_question_answer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IBB-University/ghadeer_question_answer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IBB-University/ghadeer_question_answer")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IBB-University/ghadeer_question_answer") model = AutoModelForCausalLM.from_pretrained("IBB-University/ghadeer_question_answer") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IBB-University/ghadeer_question_answer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IBB-University/ghadeer_question_answer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IBB-University/ghadeer_question_answer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IBB-University/ghadeer_question_answer
- SGLang
How to use IBB-University/ghadeer_question_answer 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 "IBB-University/ghadeer_question_answer" \ --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": "IBB-University/ghadeer_question_answer", "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 "IBB-University/ghadeer_question_answer" \ --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": "IBB-University/ghadeer_question_answer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IBB-University/ghadeer_question_answer with Docker Model Runner:
docker model run hf.co/IBB-University/ghadeer_question_answer
Commit ·
bdd8e93
1
Parent(s): 4df8b3c
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,3 +12,34 @@ widget:
|
|
| 12 |
- text: "ما حكم الاحتفال بالمولد النبوي"
|
| 13 |
- text: "ما هي الكتب السماوية"
|
| 14 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
- text: "ما حكم الاحتفال بالمولد النبوي"
|
| 13 |
- text: "ما هي الكتب السماوية"
|
| 14 |
---
|
| 15 |
+
## Testing the model using `transformers`:
|
| 16 |
+
|
| 17 |
+
```python
|
| 18 |
+
from transformers import GPT2TokenizerFast, pipeline
|
| 19 |
+
#for base and medium
|
| 20 |
+
from transformers import GPT2LMHeadModel
|
| 21 |
+
#for large and mega
|
| 22 |
+
# pip install arabert
|
| 23 |
+
from arabert.aragpt2.grover.modeling_gpt2 import GPT2LMHeadModel
|
| 24 |
+
|
| 25 |
+
from arabert.preprocess import ArabertPreprocessor
|
| 26 |
+
|
| 27 |
+
MODEL_NAME='IBB-University/ghadeer_question_answer'
|
| 28 |
+
arabert_prep = ArabertPreprocessor(model_name=MODEL_NAME)
|
| 29 |
+
|
| 30 |
+
text=""
|
| 31 |
+
text_clean = arabert_prep.preprocess(text)
|
| 32 |
+
|
| 33 |
+
model = GPT2LMHeadModel.from_pretrained(MODEL_NAME)
|
| 34 |
+
tokenizer = GPT2TokenizerFast.from_pretrained(MODEL_NAME)
|
| 35 |
+
generation_pipeline = pipeline("text-generation",model=model,tokenizer=tokenizer)
|
| 36 |
+
|
| 37 |
+
#feel free to try different decoding settings
|
| 38 |
+
generation_pipeline(text,
|
| 39 |
+
pad_token_id=tokenizer.eos_token_id,
|
| 40 |
+
num_beams=10,
|
| 41 |
+
max_length=200,
|
| 42 |
+
top_p=0.9,
|
| 43 |
+
repetition_penalty = 3.0,
|
| 44 |
+
no_repeat_ngram_size = 3)[0]['generated_text']
|
| 45 |
+
```
|