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

Libraries

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

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

pipe = pipeline("text-generation", model="rhysjones/phi-2-orange", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("rhysjones/phi-2-orange", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rhysjones/phi-2-orange 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"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhysjones/phi-2-orange",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use rhysjones/phi-2-orange 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" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhysjones/phi-2-orange",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhysjones/phi-2-orange",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rhysjones/phi-2-orange with Docker Model Runner:
```
docker model run hf.co/rhysjones/phi-2-orange
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Phi-2 Orange

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

There is an updated model at rhysjones/phi-2-orange-v2 which has higher evals, if you wish to test.

Training details

A first finetune using a collection of broad training data:

And then a DPO finetune using:

Run within Ollama

If you're using Ollama, you can download and run using:

ollama run rhysjones/phi-2-orange

Prompt Format

Phi-2 Orange uses ChatML as the prompt format, with or without the system instruction.

To 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

You can also omit the system prompt if you wish:

<|im_start|>user
Why is the sky blue?<|im_end|>
<|im_start|>assistant

Evaluations

Evaluations done using mlabonne's usefull Colab notebook llm-autoeval. Also check out the alternative leaderboard at Yet_Another_LLM_Leaderboard

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
phi-2-orange	33.37	71.33	49.87	37.3	47.97
phi-2-dpo	30.39	71.68	50.75	34.9	46.93
dolphin-2_6-phi-2	33.12	69.85	47.39	37.2	46.89
phi-2	27.98	70.8	44.43	35.21	44.61

Downloads last month: 22

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for rhysjones/phi-2-orange

Merges

10 models

Quantizations

3 models

rhysjones
/

phi-2-orange