Instructions to use BathSalt-1/daedalus-phi-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BathSalt-1/daedalus-phi-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BathSalt-1/daedalus-phi-3")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BathSalt-1/daedalus-phi-3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BathSalt-1/daedalus-phi-3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BathSalt-1/daedalus-phi-3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BathSalt-1/daedalus-phi-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BathSalt-1/daedalus-phi-3
- SGLang
How to use BathSalt-1/daedalus-phi-3 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 "BathSalt-1/daedalus-phi-3" \ --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": "BathSalt-1/daedalus-phi-3", "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 "BathSalt-1/daedalus-phi-3" \ --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": "BathSalt-1/daedalus-phi-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BathSalt-1/daedalus-phi-3 with Docker Model Runner:
docker model run hf.co/BathSalt-1/daedalus-phi-3
Create tokenizer.py
Browse files- tokenizer.py +11 -0
tokenizer.py
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
from transformers import AutoTokenizer
|
| 3 |
+
|
| 4 |
+
class BathSalt1DaedalusPhi3Tokenizer(AutoTokenizer):
|
| 5 |
+
def __init__(self, config):
|
| 6 |
+
super().__init__(config)
|
| 7 |
+
self.config = config
|
| 8 |
+
|
| 9 |
+
def encode(self, text, return_tensors="pt"):
|
| 10 |
+
encoding = super().encode(text, return_tensors=return_tensors)
|
| 11 |
+
return encoding
|