Instructions to use haijian06/Yi-1.5-6B-Chat-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haijian06/Yi-1.5-6B-Chat-Math with Transformers:

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

pipe = pipeline("text-generation", model="haijian06/Yi-1.5-6B-Chat-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("haijian06/Yi-1.5-6B-Chat-Math")
model = AutoModelForCausalLM.from_pretrained("haijian06/Yi-1.5-6B-Chat-Math")
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 haijian06/Yi-1.5-6B-Chat-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haijian06/Yi-1.5-6B-Chat-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": "haijian06/Yi-1.5-6B-Chat-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haijian06/Yi-1.5-6B-Chat-Math

SGLang

How to use haijian06/Yi-1.5-6B-Chat-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 "haijian06/Yi-1.5-6B-Chat-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": "haijian06/Yi-1.5-6B-Chat-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 "haijian06/Yi-1.5-6B-Chat-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": "haijian06/Yi-1.5-6B-Chat-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use haijian06/Yi-1.5-6B-Chat-Math with Docker Model Runner:
```
docker model run hf.co/haijian06/Yi-1.5-6B-Chat-Math
```

Yi-1.5-6B-Chat-Math

Yi-1.5-6B-Chat-Math is a specialized natural language processing model fine-tuned from Yi-1.5 to excel in mathematical problem-solving and related tasks. Designed to handle a wide range of mathematical queries, from algebra and geometry to calculus and beyond, this model serves as a powerful tool for students, educators, and researchers alike.

Features

Mathematical Problem Solving: Accurately solves various types of mathematical problems, including but not limited to algebra, geometry, and calculus.
Formula Derivation: Assists in deriving and explaining mathematical formulas to enhance understanding of complex concepts.
Multilingual Support: Capable of handling mathematical queries in multiple languages, enhancing accessibility for a diverse user base.
Custom Fine-Tuning: Trained on a proprietary dataset to ensure high performance and reliability in mathematical contexts.

Dataset

The model has been fine-tuned using a custom dataset tailored for advanced mathematical tasks. The dataset is openly available for research and development purposes.

Dataset Name: Advanced-Math
Access Link: Advanced-Math Dataset

Installation

To get started with Yi-1.5-6B-Chat-Math, ensure you have the necessary dependencies installed:

pip install transformers torch

Usage

Below is a simple example demonstrating how to use the model for solving a mathematical equation:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("haijian06/Yi-1.5-6B-Chat-Math")
model = AutoModelForCausalLM.from_pretrained("haijian06/Yi-1.5-6B-Chat-Math", torch_dtype=torch.float16, device_map="auto")

input_text = "Solve the equation x^2 - 5x + 6 = 0 Let's solve this step-by-step:"

inputs = tokenizer(input_text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=True,
        temperature=0.7,
        top_p=0.95,
    )

answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(answer)

Model answer:

Solve the equation x^2  - 5 x + 6  = 0  Let's solve this step-by-step:

Step 1: Factor the equation
The equation can be factored as follows:

x^2 - 5x + 6 = 0
(x - 2)(x - 3) = 0

Step 2: Apply the zero product property
If the product of two numbers is zero, then at least one of the numbers must be zero.

So, either (x - 2) = 0 or (x - 3) = 0

Step 3: Solve for x
If (x - 2) = 0, then x = 2
If (x - 3) = 0, then x = 3

So, the solutions are x = 2 and x = 3.

Answer: 2, 3

Contributing

Contributions are welcome! Whether you have suggestions for improvements, bug reports, or want to contribute code, feel free to open an issue or submit a pull request on GitHub.

License

This project is licensed under the Apache-2.0 License.

Contact

For more information, support, or inquiries, please visit my GitHub profile:

GitHub: https://github.com/Haijian06

Downloads last month: 2

Safetensors

Model size

6B params

Tensor type

BF16