README.md

---
base_model:
- google/gemma-3-4b-pt
pipeline_tag: text-generation
library_name: transformers
---
# **thinkygemma-4b: your average fake reasoner**
Fine-tuned from **Gemma-3-4b-pt**  

📌 **Model ID:** `xsanskarx/thinkygemma-4b`  
📌 **Parameters trained:** **1.8 billion**  
📌 **Trained on:** **25k rows of verified Chain-of-Thought (CoT) traces** from **DeepSeek R1** and **Qwen QWQ**  
📌 **Next planned step:** **GRPO** 
📌 **adapters repo:** `xsanskarx/thinkgemma-4b`


---

## **Model Description**
This is a **fine-tuned version of Google's Gemma-3-4b-it**, adapted for **structured reasoning / fake induced reasoning **. It is designed to excel in acting like a great reasoner**.  

### **Training Details**
- **Hardware:** Single NVIDIA **H100**  
- **Training Time:** **9 hours (1 epoch)**  
- **Training Method:** **LoRA fine-tuning (r = 128, alpha = 256)**  
- **Dataset:** **25k CoT traces**  
- **Base Model:** `google/gemma-3-4b-it`  

---



### **Setup**
```python
from transformers import AutoTokenizer, Gemma3ForConditionalGeneration, TextStreamer
import torch

# Load model and tokenizer
model_id = "xsanskarx/thinkygemma-4b"
model = Gemma3ForConditionalGeneration.from_pretrained(model_id, device_map="auto").eval()
tokenizer = AutoTokenizer.from_pretrained(model_id)

def ask_model(prompt: str, max_tokens=8192, temperature=0.7):
    """
    Function to ask a question to the model and stream the response.
    """
    messages = [
        {"role": "system", "content": "You are an expert math problem solver, think and reason inside <think> tags, enclose all reasoning in <think> tags, verifying logic step by step and then return your final structured answer"},
        {"role": "user", "content": prompt}
    ]

    formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False)
    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)

    streamer = TextStreamer(tokenizer, skip_special_tokens=True)
    with torch.inference_mode():
        model.generate(**inputs, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, streamer=streamer)

# Example usage
ask_model("do 2+2")