Instructions to use tursunali/bpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tursunali/bpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tursunali/bpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tursunali/bpt2") model = AutoModelForCausalLM.from_pretrained("tursunali/bpt2") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tursunali/bpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tursunali/bpt2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tursunali/bpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tursunali/bpt2
- SGLang
How to use tursunali/bpt2 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 "tursunali/bpt2" \ --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": "tursunali/bpt2", "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 "tursunali/bpt2" \ --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": "tursunali/bpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tursunali/bpt2 with Docker Model Runner:
docker model run hf.co/tursunali/bpt2
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ Please cite BPT2 as follows:
|
|
| 50 |
@misc{Backpacker_Trail_German_large_2022,
|
| 51 |
author = {BackpackerTrail, Tursunali Kholdorov},
|
| 52 |
title = {{BPT2: Backpacker Trail German versions of BPT2}},
|
| 53 |
-
url = {https://github.com/
|
| 54 |
year = {2022}
|
| 55 |
}
|
| 56 |
```
|
|
|
|
| 50 |
@misc{Backpacker_Trail_German_large_2022,
|
| 51 |
author = {BackpackerTrail, Tursunali Kholdorov},
|
| 52 |
title = {{BPT2: Backpacker Trail German versions of BPT2}},
|
| 53 |
+
url = {https://github.com/Tursunali-Kholdorov/bptTrainer},
|
| 54 |
year = {2022}
|
| 55 |
}
|
| 56 |
```
|