Instructions to use rubenroy/Zurich-1.5B-GCv2-50k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rubenroy/Zurich-1.5B-GCv2-50k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rubenroy/Zurich-1.5B-GCv2-50k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rubenroy/Zurich-1.5B-GCv2-50k")
model = AutoModelForCausalLM.from_pretrained("rubenroy/Zurich-1.5B-GCv2-50k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rubenroy/Zurich-1.5B-GCv2-50k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rubenroy/Zurich-1.5B-GCv2-50k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubenroy/Zurich-1.5B-GCv2-50k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rubenroy/Zurich-1.5B-GCv2-50k

SGLang

How to use rubenroy/Zurich-1.5B-GCv2-50k with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rubenroy/Zurich-1.5B-GCv2-50k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubenroy/Zurich-1.5B-GCv2-50k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rubenroy/Zurich-1.5B-GCv2-50k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rubenroy/Zurich-1.5B-GCv2-50k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use rubenroy/Zurich-1.5B-GCv2-50k with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rubenroy/Zurich-1.5B-GCv2-50k to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rubenroy/Zurich-1.5B-GCv2-50k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rubenroy/Zurich-1.5B-GCv2-50k to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="rubenroy/Zurich-1.5B-GCv2-50k",
    max_seq_length=2048,
)

Docker Model Runner
How to use rubenroy/Zurich-1.5B-GCv2-50k with Docker Model Runner:
```
docker model run hf.co/rubenroy/Zurich-1.5B-GCv2-50k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Zurich 1.5B GammaCorpus v2-50k

A Qwen 2.5 model fine-tuned on the GammaCorpus dataset

Overview

Zurich 1.5B GammaCorpus v2-50k is a fine-tune of Alibaba's Qwen 2.5 1.5B Instruct model. Zurich is designed to outperform other models that have a similar size while also showcasing GammaCorpus v2-50k.

Model Details

Base Model: Qwen/Qwen2.5-1.5B-Instruct
Type: Causal Language Models
Architecture: Transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Number of Parameters: 1.54B
Number of Paramaters (Non-Embedding): 1.31B
Number of Layers: 28
Number of Attention Heads (GQA): 12 for Q and 2 for KV

Training Details

Zurich-1.5B-GCv2-50k underwent fine-tuning with 1 A100 GPU for ~5 minutes and trained with the Unsloth framework. Zurich-1.5B-GCv2-50k 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;

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "rubenroy/Zurich-1.5B-GCv2-50k"

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 1.5B 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:
https://huggingface.co/collections/rubenroy/gammacorpus-v1-67935e4e52a04215f15a7a60

GammaCorpus v2

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

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

GammaCorpus CoT

Math 170k

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

GammaCorpus QA

Fact 450k

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

The link to the full GammaCorpus dataset collection can be found here.

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.