DeepMath-7B-M is a fine-tuned version of
DeepSeek-R1-Distill-Qwen-1.5B on the
GSM8K dataset. This model is designed for mathematical reasoning and problem-solving, excelling in arithmetic, algebra, and word problems.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3tokenizer = AutoTokenizer.from_pretrained("codewithdark/deepmath-7b-m")
4model = AutoModelForCausalLM.from_pretrained("codewithdark/deepmath-7b-m")
5
6input_text = "A farmer has 5 chickens and each lays 3 eggs a day. How many eggs in total after a week?"
7inputs = tokenizer(input_text, return_tensors="pt")
8outputs = model.generate(**inputs, max_length=100)
9print(tokenizer.decode(outputs[0], skip_special_tokens=True))
This model is released under the mit License.
1@misc{DeepMath-7B-M,
2 author = {Ahsan},
3 title = {DeepMath-7B-M: Fine-Tuned DeepSeek-R1-Distill-Qwen-1.5B on GSM8K},
4 year = {2025},
5 url = {https://huggingface.co/codewithdark/deepmath-7b-m}
6}
