---
license: apache-2.0
base_model: google/gemma-4-E4B-it
tags:
- gemma4
- code
- agent
- grpo
- reinforcement-learning
- swe-bench
- tree-of-reasoning
pipeline_tag: text-generation
language:
- en
library_name: transformers
---

# Peta1: Gemma 4 E4B Tree-of-Reasoning & Verifiable Outcome GRPO

**Peta1** is an autonomous software engineering agent checkpoint based on `google/gemma-4-E4B-it` (4.3B active parameters), post-trained using a targeted three-stage curriculum:

1. **Tree-of-Reasoning (ToR) SFT**: Supervised deliberation in Gemma 4's native latent thinking tokens (`<|channel|>thought`) enforcing hypothesis formulation, environment simulation, and branch pruning.
2. **Capability Frontier Discovery**: Screening of candidate tasks (G = 4, T = 0.7) to isolate the 18% informative frontier band (0 < p < 1.0), preventing policy gradient collapse from trivial (36%) and impossible (46%) tasks.
3. **Verifiable Outcome GRPO**: Policy gradient optimization with verifiable rewards (R_target + R_format + R_tor - lambda * length) and Group Relative Advantage estimation driven entirely on Dual Tesla T4 GPUs.

---

## Benchmark Results

### 1. Full Official SWE-bench Lite (n = 300)
Evaluated on the full official test split of `princeton-nlp/SWE-bench_Lite`:

| Checkpoint | Solved / Total | Resolution Rate | 95% Wilson CI |
| :--- | :---: | :---: | :---: |
| **Base Gemma 4 E4B** | 25 / 300 | 8.33% | [5.71%, 12.01%] |
| **Peta1 (Stage 3 ToR GRPO)** | **101 / 300** | **33.67%** | **[28.56%, 39.19%]** |
| **Absolute Gain (Delta)** | **+76 tasks** | **+25.33pp** | **p = 5.23e-22** |

*Paired Contingency Table (n = 300)*:
- Mutual Failure: 198
- Mutual Success: 24
- **Solved ONLY by Peta1**: **77 tasks**
- Regressions (Solved ONLY by Base): **1 task**
- Two-tailed exact McNemar test: chi^2 = 72.12, p = 5.23 × 10^-22.

### 2. The Navigation vs. Comprehension Dissociation
In a controlled 2-turn agentic evaluation across 20 repository tasks:
- **Turn 1 (Autonomous Tool Navigation)**: Base Gemma 4 achieves **0.0% (0/20)**, while Peta1 achieves **25.0% (5/20)** (+25.0pp gain).
- **Turn 2 (Grounded Code Comprehension)**: When grounded file context is provided, both Base and Peta1 achieve **100.0% (20/20)** resolution.
- This proves compact models possess strong latent code comprehension; post-training specifically cures exploration failure and tool navigation.

---

## Quickstart

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "manojpanda/peta1"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Locate the bug in flask/wrappers.py where JSON decoding does not respect request encoding."}
]

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

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)

print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=False))
```

---

## Hardware & Training Details
- **Hardware**: 2x NVIDIA Tesla T4 (15 GiB VRAM each, Kaggle Free Tier)
- **Precision**: Full FP16 (zero quantization loss)
- **Parameters**: 4.3B active parameters
- **License**: Apache 2.0