Instructions to use codewithdark/deepmath-7b-m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codewithdark/deepmath-7b-m with Transformers:

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

pipe = pipeline("text-generation", model="codewithdark/deepmath-7b-m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codewithdark/deepmath-7b-m")
model = AutoModelForCausalLM.from_pretrained("codewithdark/deepmath-7b-m", device_map="auto")
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 Settings

vLLM

How to use codewithdark/deepmath-7b-m with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codewithdark/deepmath-7b-m

SGLang

How to use codewithdark/deepmath-7b-m 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 "codewithdark/deepmath-7b-m" \
    --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": "codewithdark/deepmath-7b-m",
		"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 "codewithdark/deepmath-7b-m" \
        --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": "codewithdark/deepmath-7b-m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codewithdark/deepmath-7b-m with Docker Model Runner:
```
docker model run hf.co/codewithdark/deepmath-7b-m
```

deepmath-7b-m / README.md

codewithdark

Update README.md

3face5d verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.8 kB

	---
	library_name: transformers
	tags:
	- math
	license: mit
	datasets:
	- openai/gsm8k
	language:
	- en
	base_model:
	- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
	pipeline_tag: text-generation
	---


	# DeepMath-7B-M

	## Model Overview
	DeepMath-7B-M is a fine-tuned version of [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [GSM8K dataset](https://huggingface.co/datasets/gsm8k). This model is designed for mathematical reasoning and problem-solving, excelling in arithmetic, algebra, and word problems.

	## Model Details
	- Base Model: DeepSeek-R1-Distill-Qwen-1.5B
	- Fine-Tuning Dataset: GSM8K
	- Parameters: 1.5 Billion
	- Task: Mathematical Question Answering (Math QA)
	- Repository: [codewithdark/deepmath-7b-m](https://huggingface.co/codewithdark/deepmath-7b-m)
	- Commit Message: "Full merged model for math QA"

	## Training Details
	- Dataset: GSM8K (Grade School Math 8K) - a high-quality dataset for mathematical reasoning
	- Fine-Tuning Framework: Hugging Face Transformers & PyTorch
	- Optimization Techniques:
	- AdamW Optimizer
	- Learning rate scheduling
	- Gradient accumulation
	- Mixed precision training (FP16)
	- Training Steps: Multiple epochs on a high-performance GPU cluster

	## Capabilities & Performance
	DeepMath-7B-M excels in:
	- Solving word problems with step-by-step reasoning
	- Performing algebraic and arithmetic computations
	- Understanding complex problem structures
	- Generating structured solutions with explanations

	## Usage
	You can load and use the model via the Hugging Face `transformers` library:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	tokenizer = AutoTokenizer.from_pretrained("codewithdark/deepmath-7b-m")
	model = AutoModelForCausalLM.from_pretrained("codewithdark/deepmath-7b-m")

	input_text = "A farmer has 5 chickens and each lays 3 eggs a day. How many eggs in total after a week?"
	inputs = tokenizer(input_text, return_tensors="pt")
	outputs = model.generate(**inputs, max_length=100)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Limitations
	- May struggle with extremely complex mathematical proofs
	- Performance is limited to the scope of GSM8K-type problems
	- Potential biases in training data

	## Future Work
	- Extending training to more diverse math datasets
	- Exploring larger models for improved accuracy
	- Fine-tuning on physics and higher-level mathematical reasoning datasets

	## License
	This model is released under the mit License.

	## Citation
	If you use this model, please cite:
	```bibtex
	@misc{DeepMath-7B-M,
	author = {Ahsan},
	title = {DeepMath-7B-M: Fine-Tuned DeepSeek-R1-Distill-Qwen-1.5B on GSM8K},
	year = {2025},
	url = {https://huggingface.co/codewithdark/deepmath-7b-m}
	}
	```