---
base_model: Qwen/Qwen2.5-14B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- gammacorpus
- zurich
- chat
- conversational
license: apache-2.0
language:
- en
datasets:
- rubenroy/GammaCorpus-v2-5m
pipeline_tag: text-generation
library_name: transformers
---

![Zunich Banner](https://cdn.ruben-roy.com/AI/Zurich/img/banner-14B-5m.png)

# Zurich 14B GammaCorpus v2-5m
*A Qwen 2.5 model fine-tuned on the GammaCorpus dataset*

## Overview
Zurich 14B GammaCorpus v2-5m is a fine-tune of Alibaba's **Qwen 2.5 14B Instruct** model. Zurich is designed to outperform other models that have a similar size while also showcasing [GammaCorpus v2-5m](https://huggingface.co/datasets/rubenroy/GammaCorpus-v2-5m).

## Model Details
- **Base Model:** [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
- **Type:** Causal Language Models
- **Architecture:** Transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
- **Number of Parameters:** 14.7B
- **Number of Paramaters (Non-Embedding):** 13.1B
- **Number of Layers:** 48
- **Number of Attention Heads (GQA):** 40 for Q and 8 for KV

## Training Details

Zurich-14B-GCv2-5m underwent fine-tuning with 1 A100 GPU for ~90 minutes and trained with the [Unsloth](https://unsloth.ai/) framework. Zurich-14B-GCv2-5m was trained for **60 Epochs**. 

## Usage

### Requirements

We **strongly** recommend you use the latest version of the `transformers` package. You may install it via `pip` as follows:

```
pip install transformers
```

### Quickstart

Here is a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents;

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "rubenroy/Zurich-14B-GCv2-5m"

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

prompt = "How tall is the Eiffel tower?"
messages = [
    {"role": "system", "content": "You are Zurich, an AI assistant built on the Qwen 2.5 14B model developed by Alibaba Cloud, and fine-tuned by Ruben Roy. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```

## About GammaCorpus

This model, and all Zurich models, are trained with GammaCorpus. GammaCorpus is a dataset on HuggingFace that is filled with structured and filtered multi-turn conversations.
GammaCorpus has 4 version with different sizes in each. These are the following versions and sizes:

### GammaCorpus v1
- 10k UNFILTERED
- 50k UNFILTERED
- 70k UNFILTERED

Here is a link to the GCv1 dataset collection:<br>
https://huggingface.co/collections/rubenroy/gammacorpus-v1-67935e4e52a04215f15a7a60

### GammaCorpus v2
- 10k
- 50k
- 100k
- 500k
- 1m
- **5m <-- This is the version of GammaCorpus v2 that the Zurich model you are using was trained on.**

Here is a link to the GCv2 dataset collection:<br>
https://huggingface.co/collections/rubenroy/gammacorpus-v2-67935e895e1259c404a579df

### GammaCorpus CoT
- Math 170k

Here is a link to the GC-CoT dataset collection:<br>
https://huggingface.co/collections/rubenroy/gammacorpus-cot-6795bbc950b62b1ced41d14f

### GammaCorpus QA
- Fact 450k

Here is a link to the GC-QA dataset collection:<br>
https://huggingface.co/collections/rubenroy/gammacorpus-qa-679857017bb3855234c1d8c7

### The link to the full GammaCorpus dataset collection can be found [here](https://huggingface.co/collections/rubenroy/gammacorpus-67765abf607615a0eb6d61ac).

## Known Limitations

- **Bias:** We have tried our best to mitigate as much bias we can, but please be aware of the possibility that the model might generate some biased answers.

## Additional Information

### Licensing Information

The model is released under the **[Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0)**. Please refer to the license for usage rights and restrictions.