---
base_model: OctoAI/OctoThinker-3B
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- spiral
- self-play
- reinforcement-learning
- octothinker
- multi-agent
---

# SPIRAL OctoThinker-3B Multi-Agent Model

This model was trained using the SPIRAL (Self-Play Iterative Reinforcement learning for Adaptation and Learning) framework.

## Model Details

- **Base Model**: OctoAI/OctoThinker-3B
- **Training Framework**: SPIRAL
- **Checkpoint**: step_00128
- **Model Size**: 3B parameters
- **Training Date**: 2025-09-09

## Training Configuration

The model was trained with self-play on multiple environments:
- KuhnPoker-v1
- TicTacToe-v0  
- SimpleNegotiation-v2

### Training Parameters
```json
{
  "learning_rate": "1e-6",
  "train_batch_size": 128,
  "num_ppo_epochs": 2,
  "temperature": 1.0,
  "max_model_len": 16384,
  "environments": [
    "KuhnPoker-v1",
    "TicTacToe-v0",
    "SimpleNegotiation-v2"
  ],
  "base_model": "OctoAI/OctoThinker-3B",
  "framework": "SPIRAL"
}
```

## Usage

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

tokenizer = AutoTokenizer.from_pretrained("the-acorn-ai/spiral-octothinker-3b-multi-env-new-step00128")
model = AutoModelForCausalLM.from_pretrained(
    "the-acorn-ai/spiral-octothinker-3b-multi-env-new-step00128",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Generate text
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
```

## License

This model is licensed under the Apache License 2.0.