Instructions to use BucketOfFish/simplified_phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BucketOfFish/simplified_phi2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BucketOfFish/simplified_phi2", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BucketOfFish/simplified_phi2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BucketOfFish/simplified_phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BucketOfFish/simplified_phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BucketOfFish/simplified_phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BucketOfFish/simplified_phi2

SGLang

How to use BucketOfFish/simplified_phi2 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 "BucketOfFish/simplified_phi2" \
    --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": "BucketOfFish/simplified_phi2",
		"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 "BucketOfFish/simplified_phi2" \
        --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": "BucketOfFish/simplified_phi2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BucketOfFish/simplified_phi2 with Docker Model Runner:
```
docker model run hf.co/BucketOfFish/simplified_phi2
```

BucketOfFish commited on Jan 2, 2024

Commit

16cc769

1 Parent(s): a420fe7

Updated imports in script

Browse files

Files changed (1) hide show

streaming_inference.py +6 -6

streaming_inference.py CHANGED Viewed

@@ -3,8 +3,8 @@ from threading import Thread
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 import torch
-from .configuration_phi import PhiConfig
-from .modeling_phi import PhiForCausalLM
 # This works, but is not streaming
@@ -12,8 +12,8 @@ from .modeling_phi import PhiForCausalLM
 if __name__ == "__main__":
     device = "cuda"
-    model_config = PhiConfig(**json.load(open("simplified_phi2/config.json")))
-    model = PhiForCausalLM(model_config).to(device)
     phi_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
     model.load_state_dict(phi_model.state_dict())
@@ -45,8 +45,8 @@ if __name__ == "__main__":
     # make model and run model.generate(streamer=TextIteratorStreamer) on a thread
     device = "cuda"
-    model_config = PhiConfig(**json.load(open("simplified_phi2/config.json")))
-    model = PhiForCausalLM(model_config).to(device)
     phi_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
     model.load_state_dict(phi_model.state_dict())
     thread = Thread(

 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 import torch
+from .phi2_configuration import Phi2Config
+from .phi2_model import Phi2ModelForCausalLM
 # This works, but is not streaming
 if __name__ == "__main__":
     device = "cuda"
+    model_config = Phi2Config(**json.load(open("simplified_phi2/config.json")))
+    model = Phi2ModelForCausalLM(model_config).to(device)
     phi_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
     model.load_state_dict(phi_model.state_dict())
     # make model and run model.generate(streamer=TextIteratorStreamer) on a thread
     device = "cuda"
+    model_config = Phi2Config(**json.load(open("simplified_phi2/config.json")))
+    model = Phi2ModelForCausalLM(model_config).to(device)
     phi_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
     model.load_state_dict(phi_model.state_dict())
     thread = Thread(