Instructions to use IBB-University/ghadeer_question_answer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

GhadeerALbadani commited on Dec 28, 2023

Commit

7646c36

1 Parent(s): 3125d16

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -39,11 +39,7 @@ generation_pipeline = pipeline("text-generation",model=model,tokenizer=tokenizer
 #feel free to try different decoding settings
 generation_pipeline(text,
     pad_token_id=tokenizer.eos_token_id,
-    num_beams=10,
-    max_length=512,
     penalty_alpha=0.6,
-    top_p=0.9,
-    top_k=4,
-    repetition_penalty = 3.0,
-    no_repeat_ngram_size = 3)[0]['generated_text']
 ```

 #feel free to try different decoding settings
 generation_pipeline(text,
     pad_token_id=tokenizer.eos_token_id,
+     max_length=512,
     penalty_alpha=0.6,
+    top_k=4 )[0]['generated_text']
 ```