Instructions to use p1atdev/dart-v1-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use p1atdev/dart-v1-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="p1atdev/dart-v1-base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("p1atdev/dart-v1-base") model = AutoModelForCausalLM.from_pretrained("p1atdev/dart-v1-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use p1atdev/dart-v1-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "p1atdev/dart-v1-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "p1atdev/dart-v1-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/p1atdev/dart-v1-base
- SGLang
How to use p1atdev/dart-v1-base 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 "p1atdev/dart-v1-base" \ --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": "p1atdev/dart-v1-base", "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 "p1atdev/dart-v1-base" \ --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": "p1atdev/dart-v1-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use p1atdev/dart-v1-base with Docker Model Runner:
docker model run hf.co/p1atdev/dart-v1-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -56,7 +56,7 @@ inputs = tokenizer.apply_chat_template({
|
|
| 56 |
"copyright": "original",
|
| 57 |
"character": "",
|
| 58 |
"general": "1girl"
|
| 59 |
-
}, tokenize=True) # tokenize=False to preview prompt
|
| 60 |
# same as input_ids of "<|bos|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general>1girl"
|
| 61 |
|
| 62 |
with torch.no_grad():
|
|
@@ -108,7 +108,7 @@ inputs = tokenizer.apply_chat_template({
|
|
| 108 |
"copyright": "original",
|
| 109 |
"character": "",
|
| 110 |
"general": "1girl"
|
| 111 |
-
}, tokenize=True)
|
| 112 |
|
| 113 |
with torch.no_grad():
|
| 114 |
outputs = ort_model.generate(inputs, generation_config=generation_config)
|
|
|
|
| 56 |
"copyright": "original",
|
| 57 |
"character": "",
|
| 58 |
"general": "1girl"
|
| 59 |
+
}, return_tensors="pt", tokenize=True) # tokenize=False to preview prompt
|
| 60 |
# same as input_ids of "<|bos|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general>1girl"
|
| 61 |
|
| 62 |
with torch.no_grad():
|
|
|
|
| 108 |
"copyright": "original",
|
| 109 |
"character": "",
|
| 110 |
"general": "1girl"
|
| 111 |
+
}, return_tensors="pt", tokenize=True,)
|
| 112 |
|
| 113 |
with torch.no_grad():
|
| 114 |
outputs = ort_model.generate(inputs, generation_config=generation_config)
|