You can deploy this model and start earning money today!

adeelahmad/
Qwen3-4B-Thinking-2507-math

Name: Qwen3-4B-Thinking-2507-math
Availability: InStock

safetensors

qwen3

Views

No views yet

Qwen3-4B-Thinking-2507-math

Fine-tuned Qwen3-4B-Thinking-2507 model optimized for mathematical problem solving.

Model Details

Base Model: Qwen/Qwen3-4B-Thinking-2507
Fine-tuning: GRPO (Group Relative Policy Optimization)
Task: Mathematical reasoning with chain-of-thought

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "adeelahmad/Qwen3-4B-Thinking-2507-math"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")