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

Libraries

How to use hyperspaceai/hyperEngine_aligned with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hyperspaceai/hyperEngine_aligned")
model = AutoModelForCausalLM.from_pretrained("hyperspaceai/hyperEngine_aligned")
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_aligned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyperspaceai/hyperEngine_aligned"
# 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_aligned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyperspaceai/hyperEngine_aligned

SGLang

How to use hyperspaceai/hyperEngine_aligned 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_aligned" \
    --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_aligned",
		"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_aligned" \
        --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_aligned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

parthhyperspace commited on Apr 19, 2024

Commit

4a10d33

verified ·

1 Parent(s): 67547e3

Changed Classification

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -2,8 +2,6 @@
 language:
 - en
 license: apache-2.0
-tags:
-- mlx
 base_model: alpindale/Mistral-7B-v0.2-hf
 datasets:
 - cognitivecomputations/dolphin
@@ -26,6 +24,7 @@ model-index:
       value: 0.469
       name: pass@1
       verified: false
 ---
 # hyperspaceai/hyperEngine_aligned
@@ -42,4 +41,4 @@ from mlx_lm import load, generate
 model, tokenizer = load("hyperspaceai/hyperEngine_aligned")
 response = generate(model, tokenizer, prompt="hello", verbose=True)
-```

 language:
 - en
 license: apache-2.0
 base_model: alpindale/Mistral-7B-v0.2-hf
 datasets:
 - cognitivecomputations/dolphin
       value: 0.469
       name: pass@1
       verified: false
+pipeline_tag: text-generation
 ---
 # hyperspaceai/hyperEngine_aligned
 model, tokenizer = load("hyperspaceai/hyperEngine_aligned")
 response = generate(model, tokenizer, prompt="hello", verbose=True)
+```