Instructions to use jrc/phi3-mini-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jrc/phi3-mini-math with Transformers:

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

pipe = pipeline("text-generation", model="jrc/phi3-mini-math", 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("jrc/phi3-mini-math", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jrc/phi3-mini-math", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jrc/phi3-mini-math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jrc/phi3-mini-math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jrc/phi3-mini-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jrc/phi3-mini-math

SGLang

How to use jrc/phi3-mini-math 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 "jrc/phi3-mini-math" \
    --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": "jrc/phi3-mini-math",
		"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 "jrc/phi3-mini-math" \
        --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": "jrc/phi3-mini-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jrc/phi3-mini-math with Docker Model Runner:
```
docker model run hf.co/jrc/phi3-mini-math
```

jrc/phi3-mini-math

Math majors - who needs em? This model can answer any math questions you have.

How to Get Started with the Model

Use the code below to get started with the model.

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jrc/phi3-mini-math", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jrc/phi3-mini-math", trust_remote_code=True)

Training Details

Phi3 was trained using torchtune and the training script + config file are located in this repository.

tune run lora_finetune_distributed.py --config mini_lora.yaml

You can see a full Weights & Biases run here.

Training Data

This model was finetuned on the following datasets:

TIGER-Lab/MATH-plus: An advanced math-specific dataset with 894k samples.

Hardware

Machines: 4 x NVIDIA A100 GPUs
Max VRAM used per GPU: 29 GB
Real time: 10 hours

Evaluation

The finetuned model is evaluated on minerva-math using EleutherAI Eval Harness through torchtune.

tune run eleuther_eval --config eleuther_evaluation \
          checkpoint.checkpoint_dir=./lora-phi3-math \
          tasks=["minerva_math"] \
          batch_size=32

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
minerva_math	N/A	none	4	exact_match	0.1670	±	0.0051
- minerva_math_algebra	1	none	4	exact_match	0.2502	±	0.0126
- minerva_math_counting_and_prob	1	none	4	exact_match	0.1329	±	0.0156
- minerva_math_geometry	1	none	4	exact_match	0.1232	±	0.0150
- minerva_math_intermediate_algebra	1	none	4	exact_match	0.0576	±	0.0078
- minerva_math_num_theory	1	none	4	exact_match	0.1148	±	0.0137
- minerva_math_prealgebra	1	none	4	exact_match	0.3077	±	0.0156
- minerva_math_precalc	1	none	4	exact_match	0.0623	±	0.0104

This shows a large improvement over the base Phi3 Mini model.

Model Card Contact

Drop me a line at @official_j3rck

Downloads last month: 11

jrc
/

phi3-mini-math