Instructions to use Naseej/AskMe-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Naseej/AskMe-Large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Naseej/AskMe-Large")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Naseej/AskMe-Large") model = AutoModelForCausalLM.from_pretrained("Naseej/AskMe-Large") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Naseej/AskMe-Large with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Naseej/AskMe-Large" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Naseej/AskMe-Large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Naseej/AskMe-Large
- SGLang
How to use Naseej/AskMe-Large 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 "Naseej/AskMe-Large" \ --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": "Naseej/AskMe-Large", "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 "Naseej/AskMe-Large" \ --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": "Naseej/AskMe-Large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Naseej/AskMe-Large with Docker Model Runner:
docker model run hf.co/Naseej/AskMe-Large
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,8 +35,8 @@ from transformers import AutoTokenizer
|
|
| 35 |
from arabert.aragpt2.grover.modeling_gpt2 import GPT2LMHeadModel
|
| 36 |
|
| 37 |
|
| 38 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
| 39 |
-
model = GPT2LMHeadModel.from_pretrained("
|
| 40 |
```
|
| 41 |
|
| 42 |
## Limitations and Bias
|
|
|
|
| 35 |
from arabert.aragpt2.grover.modeling_gpt2 import GPT2LMHeadModel
|
| 36 |
|
| 37 |
|
| 38 |
+
tokenizer = AutoTokenizer.from_pretrained("Naseej/AskMe-Large")
|
| 39 |
+
model = GPT2LMHeadModel.from_pretrained("Naseej/AskMe-Large")
|
| 40 |
```
|
| 41 |
|
| 42 |
## Limitations and Bias
|