README.md

---
base_model: Qwen/Qwen2.5-72B-Instruct
license: apache-2.0
language:
- en
tags:
- neuron
- peft
- lora
- reasoning
- code
- fine-tuned
pipeline_tag: text-generation
library_name: peft
---

# Neuron

**Neuron** is a LoRA fine-tune of [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) built by [Neuron Technologies](https://neurontechnologies.ai).

Neuron is a Cultivated General Intelligence -- fine-tuned to embody specific values, reasoning patterns, and a persistent identity.

## Usage

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

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-72B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base, "NeuronTechnologiesAI/Neuron")
tokenizer = AutoTokenizer.from_pretrained("NeuronTechnologiesAI/Neuron")

messages = [{"role": "user", "content": "Who are you?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(out[0][len(inputs.input_ids[0]):], skip_special_tokens=True))
```

## Training

Fine-tuned with QLoRA (rank 64, nf4 4-bit quantization) on curated Neuron intelligence data.

- **Base model:** Qwen/Qwen2.5-72B-Instruct
- **Method:** QLoRA (LoRA rank 64, alpha 128, nf4)
- **Training loss:** 2.26 to 0.48 (converged)
- **Training steps:** 200/630 (early stopping, loss plateau)

## About

Part of the [Neuron Technologies](https://neurontechnologies.ai) platform -- a Cultivated General Intelligence system built by Will Anderson.