Instructions to use rhysjones/phi-2-orange-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rhysjones/phi-2-orange-v2 with Transformers:

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

pipe = pipeline("text-generation", model="rhysjones/phi-2-orange-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rhysjones/phi-2-orange-v2")
model = AutoModelForCausalLM.from_pretrained("rhysjones/phi-2-orange-v2", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rhysjones/phi-2-orange-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rhysjones/phi-2-orange-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhysjones/phi-2-orange-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rhysjones/phi-2-orange-v2

SGLang

How to use rhysjones/phi-2-orange-v2 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 "rhysjones/phi-2-orange-v2" \
    --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": "rhysjones/phi-2-orange-v2",
		"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 "rhysjones/phi-2-orange-v2" \
        --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": "rhysjones/phi-2-orange-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rhysjones/phi-2-orange-v2 with Docker Model Runner:
```
docker model run hf.co/rhysjones/phi-2-orange-v2
```

rhysjones commited on Mar 17, 2024

Commit

0144067

verified ·

1 Parent(s): bd8dc8f

Update prompting suggestions

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -11,6 +11,7 @@ datasets:
 - argilla/ultrafeedback-binarized-preferences-cleaned
 widget:
   - example_title: "Example interaction"
     text: "Why is the sky blue?"
 model-index:
 - name: phi-2-orange-v2
@@ -133,7 +134,7 @@ within Hugging Face's Transformers library (without the need for trust remote co
 Phi-2 Orange v2 uses ChatML as the prompt format, with or without the system instruction.
 (Update 12th March 2024: fixed eos_token issue)
-To prompt with a system instruction (use whatever system prompt you like):
 ```
 <|im_start|>system
@@ -144,13 +145,14 @@ Write a function to calculate the Fibonacci sequence<|im_end|>
 ```
-You can also omit the system prompt if you wish:
 ```
 <|im_start|>user
-Why is the sky blue?<|im_end|>
 <|im_start|>assistant
 ```
 # Evaluations

 - argilla/ultrafeedback-binarized-preferences-cleaned
 widget:
   - example_title: "Example interaction"
+    context: "You are a helpful assistant. Be short and direct in your answers."
     text: "Why is the sky blue?"
 model-index:
 - name: phi-2-orange-v2
 Phi-2 Orange v2 uses ChatML as the prompt format, with or without the system instruction.
 (Update 12th March 2024: fixed eos_token issue)
+It's recommended to always prompt with a system instruction (use whatever system prompt you like):
 ```
 <|im_start|>system
 ```
+For example, if you find the model's output to be overly verbose, instruct it to be short and concise:
 ```
+<|im_start|>system
+You are a helpful assistant. Be short and direct in your answers.<|im_end|>
 <|im_start|>user
+Was Tom Hanks in the movie Forrest Gump? If so, who did he play and give details of the plot.<|im_end|>
 <|im_start|>assistant
 ```
 # Evaluations