---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- fableforge
- nexus
- domain-specialist
- uncensored
- qwen2.5
- 1.5b
- merged
- lora
base_model: Qwen/Qwen2.5-1.5B-Instruct
---

# NEXUS-Coder

Specialized code generation and analysis model

## Description

Fine-tuned for code generation, debugging, code review, and software architecture across multiple programming languages.

This model was created by merging a domain-specialized LoRA adapter onto [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct). It is part of the **NEXUS** model series by FableForge AI — a collection of uncensored, domain-expert small language models.

## Training

- **Base Model:** Qwen/Qwen2.5-1.5B-Instruct
- **Method:** QLoRA (r=16, alpha=16)
- **Format:** 4-bit NF4 quantized LoRA, merged to bfloat16
- **Data:** Domain-curated subset of the FableForge NEXUS training corpus (18 curated sources, ~162K examples)
- **License:** Apache 2.0

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("fableforge-ai/NEXUS-Coder", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("fableforge-ai/NEXUS-Coder")

prompt = "<your prompt here>"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0]))
```

## Ollama

```bash
ollama pull fableforge-ai/nexus-coder
```

## Quantized GGUF Versions

Quantized GGUF versions for llama.cpp / Ollama are available:

- [King3Djbl/NEXUS-Coder-GGUF](https://huggingface.co/King3Djbl/NEXUS-Coder-GGUF)

Includes all standard quantization formats from Q2_K through Q8_0 and F16.

## Benchmarks

This model achieves strong performance on domain-specific tasks while maintaining a compact 1.5B parameter footprint. See the GGUF repository for detailed benchmark results across standard evaluation suites.