Instructions to use hyperspaceai/hyperEngine_phi3_128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyperspaceai/hyperEngine_phi3_128k with Transformers:

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

pipe = pipeline("text-generation", model="hyperspaceai/hyperEngine_phi3_128k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hyperspaceai/hyperEngine_phi3_128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hyperspaceai/hyperEngine_phi3_128k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hyperspaceai/hyperEngine_phi3_128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyperspaceai/hyperEngine_phi3_128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/hyperEngine_phi3_128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyperspaceai/hyperEngine_phi3_128k

SGLang

How to use hyperspaceai/hyperEngine_phi3_128k 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 "hyperspaceai/hyperEngine_phi3_128k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/hyperEngine_phi3_128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "hyperspaceai/hyperEngine_phi3_128k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/hyperEngine_phi3_128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hyperspaceai/hyperEngine_phi3_128k with Docker Model Runner:
```
docker model run hf.co/hyperspaceai/hyperEngine_phi3_128k
```

pragneshbarik commited on Apr 27, 2024

Commit

8c26326

1 Parent(s): 3dfb844

hardcoded model

Browse files

Files changed (1) hide show

handler.py +4 -3

handler.py CHANGED Viewed

@@ -1,12 +1,13 @@
 from typing import Dict, List, Any
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 class EndpointHandler():
     def __init__(self, path=""):
-        self.model = AutoModelForCausalLM.from_pretrained(path, device_map="cuda", torch_dtype="auto", trust_remote_code=True)
-        self.tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
-        self.pipe = pipeline("text-generation", model=self.model, tokenizer=self.tokenizer)
     def __call__(self, data:Dict[str, Any]) :
         messages = data.pop("messages", None)

+import torch
 from typing import Dict, List, Any
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 class EndpointHandler():
     def __init__(self, path=""):
+        model = AutoModelForCausalLM.from_pretrained("hyperspaceai/hyperEngine_phi3_128k", device_map="auto", torch_dtype="auto", trust_remote_code=True)
+        tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
+        self.pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
     def __call__(self, data:Dict[str, Any]) :
         messages = data.pop("messages", None)