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)

# 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")
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 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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Phi-2 Orange Version 2

A two-step finetune of Phi-2, with a bit more zest.

This is an improved version of the original Phi-2-Orange that uses an updated training process on the same datasets.

It also uses the latest updated model from Microsoft's Phi-2, making it directly usable within Hugging Face's Transformers library (without the need for trust remote code).

Prompt Format

Phi-2 Orange v2 uses ChatML as the prompt format.
(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
You are a helpful assistant for Python which outputs in Markdown format.<|im_end|>
<|im_start|>user
Write a function to calculate the Fibonacci sequence<|im_end|>
<|im_start|>assistant

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

Open LLM Leaderboard Evaluation Results
Detailed results can be found here

Metric	Value
Average	63.67
AI2 Reasoning Challenge (25-Shot)	61.86
HellaSwag (10-Shot)	76.32
MMLU (5-Shot)	55.72
TruthfulQA (0-shot)	54.84
Winogrande (5-shot)	75.69
GSM8k (5-shot)	57.62

YALL - Yet Another LLM Leaderboard
Evaluation from mlabonne's alternative LLM leaderboard:

Metric	Value
Average	49.64
AGIEval	34.55
GPT4All	70.96
TruthfulQA	54.87
Bigbench	38.17

Limitations

This model shares the same limitations as the underlying Phi-2 model, details of which are found here.

Downloads last month: 79

Safetensors

Model size

3B params

Tensor type

F16

Model tree for rhysjones/phi-2-orange-v2

Adapters

2 models

Finetunes

1 model

Merges

4 models

Quantizations

4 models

Datasets used to train rhysjones/phi-2-orange-v2

Space using rhysjones/phi-2-orange-v2 1

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

61.860
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

76.320
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

55.720
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

54.840
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

75.690
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

57.620