---
license: gemma
language:
- en
pipeline_tag: text-generation
tags:
- nlp
---

# Gemma-2B-Tele-it Model Card

## Model Summary

The language model Gemma-2B-Tele-it is an instruct version of [Gemma-2B-Tele](https://huggingface.co/AliMaatouk/Gemma-2B-Tele), which is based on Google [gemma-2b](https://huggingface.co/google/gemma-2b) and specialized in telecommunications. It was fine-tuned to follow instructions using Supervised Fine-tuning (SFT) with a combination of the [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) and [Open-instruct](https://huggingface.co/datasets/VMware/open-instruct) datasets. 

### Context Length

The context length of the model is 8192 tokens.

## Usage

Gemma-2B-Tele-it has been fine-tuned using pairs of instructions and responses from the [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) and [Open-instruct](https://huggingface.co/datasets/VMware/open-instruct) datasets, separated by the "\n" delimiter. Below is an example of how to query the model using this format:

```markdown
Prompt: Explain to me Shannon capacity.\n

Model: Shannon capacity is a measure of the maximum achievable rate of reliable data transmission that can occur over a noisy channel, named after C. E. Shannon. It is also commonly known as channel capacity in information theory, and it is the largest amount of information that a channel can transmit reliably per unit of time. It is calculated by considering the noise and interference that a transmission may face.
``` 

## Sample Code

Below we share some code snippets on how to get quickly started with running the model. First, make sure to `pip install transformers`, then copy the snippet corresponding to your hardware and adapt it to your usecase.

#### Running the model on a CPU


```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("AliMaatouk/Gemma-2B-Tele-it", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Gemma-2B-Tele-it")

prompt = "Explain to me Shannon capacity.\n"
input_ids = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**input_ids, max_new_tokens=100)

generated_tokens = outputs[0, len(input_ids['input_ids'][0]):]
response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(response)
```

#### Running the model on a single / multi GPU

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

model = AutoModelForCausalLM.from_pretrained("AliMaatouk/Gemma-2B-Tele-it", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Gemma-2B-Tele-it")

prompt = "Explain to me Shannon capacity.\n"
input_ids = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=100)

generated_tokens = outputs[0, len(input_ids['input_ids'][0]):]
response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(response)
```

## Citation

You can find the paper with all details about the model at https://arxiv.org/abs/2409.05314. Please cite it as follows:

```bib
@misc{maatouk2024telellmsseriesspecializedlarge,
      title={Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications}, 
      author={Ali Maatouk and Kenny Chirino Ampudia and Rex Ying and Leandros Tassiulas},
      year={2024},
      eprint={2409.05314},
      archivePrefix={arXiv},
      primaryClass={cs.IT},
      url={https://arxiv.org/abs/2409.05314}, 
}
```