Instructions to use prithivMLmods/Math-IIO-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Math-IIO-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Math-IIO-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Math-IIO-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Math-IIO-7B-Instruct")
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 prithivMLmods/Math-IIO-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Math-IIO-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Math-IIO-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Math-IIO-7B-Instruct

SGLang

How to use prithivMLmods/Math-IIO-7B-Instruct 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 "prithivMLmods/Math-IIO-7B-Instruct" \
    --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": "prithivMLmods/Math-IIO-7B-Instruct",
		"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 "prithivMLmods/Math-IIO-7B-Instruct" \
        --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": "prithivMLmods/Math-IIO-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Math-IIO-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Math-IIO-7B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Math IIO 7B Instruct

The Math IIO 7B Instruct is a fine-tuned language model based on the robust Qwen2.5-7B-Instruct architecture. This model has been specifically trained to excel in single-shot mathematical reasoning and instruction-based tasks, making it a reliable choice for educational, analytical, and problem-solving applications.

Key Features:

Math-Optimized Capabilities:
The model is designed to handle complex mathematical problems, step-by-step calculations, and reasoning tasks.
Instruction-Tuned:
Fine-tuned for better adherence to structured queries and task-oriented prompts, enabling clear and concise outputs.
Large Vocabulary:
Equipped with an extensive tokenizer configuration and custom tokens to ensure precise mathematical notation support.

Single Shot Answers

Math-IIO File Structure

File Name [ Uploaded file ]	Size	Description	Upload Status
`.gitattributes`	1.57 kB	Git attributes configuration file	Uploaded
`README.md`	263 Bytes	README file with minimal details	Updated
`added_tokens.json`	657 Bytes	Custom added tokens for tokenizer	Uploaded
`config.json`	861 Bytes	Model configuration file	Uploaded
`generation_config.json`	281 Bytes	Configuration for text generation settings	Uploaded
`merges.txt`	1.82 MB	Merge rules for byte pair encoding tokenizer	Uploaded
`pytorch_model-00001-of-00004.bin`	4.88 GB	First part of model weights (PyTorch)	Uploaded (LFS)
`pytorch_model-00002-of-00004.bin`	4.93 GB	Second part of model weights (PyTorch)	Uploaded (LFS)
`pytorch_model-00003-of-00004.bin`	4.33 GB	Third part of model weights (PyTorch)	Uploaded (LFS)
`pytorch_model-00004-of-00004.bin`	1.09 GB	Fourth part of model weights (PyTorch)	Uploaded (LFS)
`pytorch_model.bin.index.json`	28.1 kB	Index JSON file for model weights	Uploaded
`special_tokens_map.json`	644 Bytes	Map of special tokens used by the tokenizer	Uploaded
`tokenizer.json`	11.4 MB	Tokenizer settings and vocab	Uploaded (LFS)
`tokenizer_config.json`	7.73 kB	Configuration for tokenizer	Uploaded
`vocab.json`	2.78 MB	Vocabulary for tokenizer	Uploaded

Model Type	Size	Context Length	Link
GGUF	7B	-	🤗 Math-IIO-7B-Instruct-GGUF

Training Details:

Base Model: Qwen/Qwen2.5-7B-Instruct
Dataset: Trained on Math-IIO-68K-Mini, a curated dataset with 68.8k high-quality examples focusing on mathematical instructions, equations, and logic-based queries.

Capabilities:

Problem-Solving: Solves mathematical problems ranging from basic arithmetic to advanced calculus and linear algebra.
Educational Use: Explains solutions step-by-step, making it a valuable teaching assistant.
Analysis & Reasoning: Handles logical reasoning tasks and computational queries effectively.

How to Use:

Download all model files, ensuring the PyTorch weights and tokenizer configurations are included.
Load the model in your Python environment using frameworks like PyTorch or Hugging Face Transformers.
Use the provided configurations (config.json and generation_config.json) for optimal inference.