|
--- |
|
license: llama3 |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- nlp |
|
--- |
|
|
|
# LLama-3-8B-Tele-it Model Card |
|
|
|
## Model Summary |
|
|
|
The language model LLama-3-8B-Tele-it is an instruct version of [LLama-3-8B-Tele](https://huggingface.co/AliMaatouk/LLama-3-8B-Tele), which is based on Meta [LLama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) 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 |
|
|
|
LLama-3-8B-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 amount of information that can be transmitted reliably over a noisy communication channel. It is named after the mathematician Claude Shannon, who developed the concept in the 1940s. The capacity of a channel is determined by the amount of noise that can be tolerated and the bandwidth of the channel. |
|
|
|
The capacity of a channel is calculated using the formula: |
|
|
|
C = B * log2(1 + SNR) |
|
|
|
where C is the channel capacity, B is the bandwidth of the channel, and SNR is the signal-to-noise ratio. |
|
``` |
|
|
|
## 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/LLama-3-8B-Tele-it", torch_dtype="auto") |
|
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/LLama-3-8B-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/LLama-3-8B-Tele-it", torch_dtype="auto", device_map="auto") |
|
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/LLama-3-8B-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}, |
|
} |
|
``` |
|
|