Instructions to use rasyosef/phi-2-instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rasyosef/phi-2-instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="rasyosef/phi-2-instruct-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rasyosef/phi-2-instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("rasyosef/phi-2-instruct-v0.1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rasyosef/phi-2-instruct-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rasyosef/phi-2-instruct-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rasyosef/phi-2-instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rasyosef/phi-2-instruct-v0.1

SGLang

How to use rasyosef/phi-2-instruct-v0.1 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 "rasyosef/phi-2-instruct-v0.1" \
    --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": "rasyosef/phi-2-instruct-v0.1",
		"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 "rasyosef/phi-2-instruct-v0.1" \
        --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": "rasyosef/phi-2-instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rasyosef/phi-2-instruct-v0.1 with Docker Model Runner:
```
docker model run hf.co/rasyosef/phi-2-instruct-v0.1
```

rasyosef commited on Aug 11, 2024

Commit

a5ba6e8

verified ·

1 Parent(s): 68fbe3f

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -110,3 +110,8 @@ These benchmarks were run using EleutherAI's [lm-evaluation-harness](https://git
 |[phi-2-instruct-v0.1](https://huggingface.co/rasyosef/phi-2-instruct-v0.1)|2.7B|**39.59**|**56.75**|53.5|**49.03**|**76.01**|
 |[phi-2](https://huggingface.co/microsoft/phi-2)|2.7B|26.53|56.44|**56.70**|44.48|73.72|

 |[phi-2-instruct-v0.1](https://huggingface.co/rasyosef/phi-2-instruct-v0.1)|2.7B|**39.59**|**56.75**|53.5|**49.03**|**76.01**|
 |[phi-2](https://huggingface.co/microsoft/phi-2)|2.7B|26.53|56.44|**56.70**|44.48|73.72|
+## Code
+The following github repo contains python code for the Supervised Fine Tuning (SFT), Direct Preference Optimization(DPO), and Model Evaluation steps.
+https://github.com/rasyosef/phi-2-instruct