README.md

---
model_name: GPT-OSS AgentBoi
base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit
license: apache-2.0
language:
  - en
tags:
  - gpt-oss
  - agent
  - tool-calling
  - react
  - lora
  - unsloth
  - trl
  - reasoning
  - harmony
  - text-generation
pipeline_tag: text-generation
library_name: transformers
---

# GPT-OSS AgentBoi

A parameter-efficient fine-tuning of GPT-OSS-20B focused on improving agentic reasoning, structured tool use, and ReAct-style instruction following.

This model was fine-tuned using LoRA adapters on the ReAct subset of Agent-FLAN with the goal of making GPT-OSS more reliable at multi-step reasoning, tool selection, action-observation workflows, and structured agent behavior.

## Overview

Large language models are often strong conversationalists but can struggle with:

- Multi-step planning
- Tool selection and invocation
- ReAct-style reasoning workflows
- Structured action generation
- Separating reasoning from final responses

GPT-OSS AgentBoi adapts GPT-OSS-20B toward these agent-oriented tasks while remaining trainable on consumer hardware through parameter-efficient fine-tuning.

## Model Details

| Item | Value |
|--------|--------|
| Model Name | GPT-OSS AgentBoi |
| Author | shiv207 |
| Base Model | unsloth/gpt-oss-20b-unsloth-bnb-4bit |
| Training Method | LoRA |
| Framework | Unsloth |
| Dataset | Agent-FLAN (ReAct subset) |
| Primary Task | Agentic Tool Use |
| Language | English |
| License | Apache 2.0 |

## Training Data

The model was fine-tuned using examples from the Agent-FLAN dataset, specifically the ReAct-style instruction trajectories.

These examples teach the model to:

- Break complex tasks into intermediate steps
- Decide when tool usage is appropriate
- Generate structured actions
- Follow action-observation loops
- Produce concise final responses

## Training Setup

Training was performed using:

- GPT-OSS-20B
- Unsloth
- TRL
- LoRA adapters
- Google Colab Tesla T4 GPU

The objective was to improve agentic behavior while keeping training accessible on limited hardware.

## Intended Use

This model is intended for:

- AI agents
- Tool-calling systems
- Research assistants
- Retrieval-augmented generation workflows
- Multi-step planning tasks
- Agentic reasoning experiments

Potential applications include:

- Search agents
- Knowledge retrieval systems
- Function-calling assistants
- Research copilots
- Workflow automation agents

## Example

### User

```text
Search for the latest SpaceX launch and summarize it.
```

### Expected Agent Behavior

1. Analyze the request.
2. Determine that external information is required.
3. Generate a structured search action.
4. Process retrieved information.
5. Produce a concise final answer.

The fine-tuning objective is to increase consistency in these workflows compared to the base model.

## Loading the Model

```python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "shiv207/gpt_oss_AGENTBOI"
)
```

## Limitations

- Evaluated primarily through qualitative testing.
- No formal benchmark suite was used.
- Training utilized only a subset of Agent-FLAN.
- Performance may vary on unseen tool schemas.
- Not optimized for general-purpose instruction tuning beyond agent-oriented tasks.

## Acknowledgments

This project builds upon the work of:

- OpenAI for GPT-OSS and the Harmony conversation format.
- Unsloth for efficient GPT-OSS fine-tuning support.
- InternLM for the Agent-FLAN dataset.

## Repository

Source code and training notebook:

GitHub: https://github.com/shiv207

## Author

**shiv207**

If you find this project useful, feel free to open issues, share feedback, or build on top of it.