---
language:
- en

license: apache-2.0

pipeline_tag: text-generation

library_name: mlx

tags:
- coding
- code-generation
- agentic-ai
- software-engineering
- mlx
- qwen
- developer-tools

datasets:
- nvidia/OpenCodeInstruct

base_model:
- Qwen/Qwen2.5-3B-Instruct
---

# 🚀 BerkeliumGPT-Coder-3B

<p align="center">
  <img src="./logo.png" width="300">
</p>

<p align="center">
  <b>Production-Grade Agentic Coding Model</b>
</p>

<p align="center">
  Built for software engineering, code generation, debugging, repository understanding, and autonomous coding workflows.
</p>

## Quick Start

### Transformers

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "berkelium-ai/BerkeliumGPT-Coder-3B"

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

### MLX

```bash
mlx_lm.generate \
  --model berkelium-ai/BerkeliumGPT-Coder-3B \
  --prompt "Build a FastAPI backend."
```

### Docker Model Runner

```bash
docker model pull hf.co/berkelium-ai/BerkeliumGPT-Coder-3B
```

```bash
docker model run hf.co/berkelium-ai/BerkeliumGPT-Coder-3B
```

### Ollama (GGUF Release)

```bash
ollama run berkeliumgpt-coder
```

## Model Details

| Property | Value |
|-----------|---------|
| Model Name | BerkeliumGPT-Coder-3B |
| Base Model | Qwen2.5-3B-Instruct |
| Parameters | 3 Billion |
| Architecture | Transformer Decoder |
| Domain | Software Engineering |
| Context Length | Base Model Configuration |
| License | Apache-2.0 |

## Capabilities

- Code Generation
- Agentic Coding
- Repository Analysis
- Bug Detection
- Refactoring
- Test Generation
- Documentation Writing
- API Development
- DevOps Automation

## Supported Languages

- Python
- JavaScript
- TypeScript
- Go
- Rust
- Java
- C++
- C#
- SQL
- Bash
- HTML
- CSS

## Example Prompt

**User**

> Build a FastAPI application with JWT authentication and PostgreSQL.

**Assistant**

Generates:
- Backend API
- Database models
- Authentication system
- Docker configuration
- Unit tests

## Intended Use

BerkeliumGPT-Coder-3B is designed for:

- AI Coding Assistants
- Software Engineering Agents
- Developer Copilots
- Research
- Local Inference
- Autonomous Development Workflows

## Limitations

- Generated code should be reviewed before production deployment.
- Security auditing is recommended.
- Human validation remains essential.

## License

Apache-2.0