Instructions to use abacaj/phi-2-super with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacaj/phi-2-super with Transformers:

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

pipe = pipeline("text-generation", model="abacaj/phi-2-super", 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("abacaj/phi-2-super", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("abacaj/phi-2-super", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abacaj/phi-2-super with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacaj/phi-2-super"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacaj/phi-2-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacaj/phi-2-super

SGLang

How to use abacaj/phi-2-super 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 "abacaj/phi-2-super" \
    --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": "abacaj/phi-2-super",
		"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 "abacaj/phi-2-super" \
        --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": "abacaj/phi-2-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacaj/phi-2-super with Docker Model Runner:
```
docker model run hf.co/abacaj/phi-2-super
```

abacaj commited on Mar 1, 2024

Commit

ea86eb0

verified ·

1 Parent(s): b12bd5c

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -0

README.md CHANGED Viewed

@@ -65,6 +65,26 @@ if __name__ == "__main__":
   print(completion)
 ```
 # MT-bench / heval
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/lnFu3x1ufdpQVysIrX4-G.png)

   print(completion)
 ```
+# Chat template
+The model uses the same chat template as found in Mistral instruct models:
+```python
+text = "<|endoftext|>[INST] What is your favourite condiment? [/INST]"
+"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
+"[INST] Do you have mayonnaise recipes? [/INST]"
+```
+You don't need to do it manually if you use the HF transformers tokenizer:
+```python
+  messages = [
+      {"role": "user", "content": "Hello, who are you?"},
+      {"role": "assistant": "content": "I am ..."}
+  ]
+  inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+```
 # MT-bench / heval
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/lnFu3x1ufdpQVysIrX4-G.png)