Instructions to use entfane/math-professor-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use entfane/math-professor-3B with Transformers:

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

pipe = pipeline("text-generation", model="entfane/math-professor-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("entfane/math-professor-3B")
model = AutoModelForCausalLM.from_pretrained("entfane/math-professor-3B")
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 entfane/math-professor-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "entfane/math-professor-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "entfane/math-professor-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/entfane/math-professor-3B

SGLang

How to use entfane/math-professor-3B 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 "entfane/math-professor-3B" \
    --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": "entfane/math-professor-3B",
		"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 "entfane/math-professor-3B" \
        --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": "entfane/math-professor-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use entfane/math-professor-3B with Docker Model Runner:
```
docker model run hf.co/entfane/math-professor-3B
```

math-professor-3B / README.md

entfane

Added chat template support

578eb94 verified about 1 year ago

preview code

raw

history blame contribute delete

1.21 kB

metadata

library_name: transformers
tags:
  - trl
  - sft
datasets:
  - qwedsacf/grade-school-math-instructions
language:
  - en
base_model:
  - Qwen/Qwen2.5-3B

Math Professor 3B

This model is a math instruction fine-tuned version of Qwen2.5-3B model.

Fine-tuning dataset

Model was fine-tuned on qwedsacf/grade-school-math-instructions instruction dataset.

Inference

!pip install transformers accelerate

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "entfane/math-professor-3B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "What's the derivative of 2x^2?"}
]

input = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
encoded_input = tokenizer(input, return_tensors = "pt").to(model.device)
output = model.generate(**encoded_input, max_new_tokens=1024)
print(tokenizer.decode(output[0], skip_special_tokens=False))